© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 4664
    Prev
    Next
    INDEX
    Explanations

    names of locations and acronyms, likely related to a specific context such as news or organization names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character sequence "Al" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.75
     Dai
    -0.68
     sterling
    -0.66
    olicy
    -0.60
     Solitaire
    -0.60
     Tycoon
    -0.59
    åĤ
    -0.58
    soDeliveryDate
    -0.58
     Chaser
    -0.58
     Compton
    -0.58
    POSITIVE LOGITS
    manac
    1.33
    uminum
    1.30
    ibaba
    1.26
    chemy
    1.25
    gorithm
    1.25
    phabet
    1.22
    gorith
    1.22
    cohol
    1.20
    gebra
    1.19
    umni
    1.18
    Activations Density 0.032%

    No Known Activations