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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 9855
    Prev
    Next
    INDEX
    Explanations

    names starting with "Al"

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation "AL"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sterling
    -0.71
     neutral
    -0.67
     laps
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.64
     wip
    -0.62
     entirely
    -0.60
     breach
    -0.60
     Solitaire
    -0.58
     guiActiveUnfocused
    -0.57
    åĤ
    -0.57
    POSITIVE LOGITS
    phabet
    1.30
    uminum
    1.26
    manac
    1.26
    ibaba
    1.24
    umni
    1.24
    gorithm
    1.23
    cohol
    1.23
    gorith
    1.21
    bum
    1.21
    buquerque
    1.21
    Activations Density 0.021%

    No Known Activations