© 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 EvalsExportsinterp-engineNEWAPI 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. 11676
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific topic or entity represented by the abbreviation 'SP'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "SP" followed by various contextual terms

    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
    taboola
    -0.71
    omorph
    -0.62
     behold
    -0.62
    naires
    -0.61
     subord
    -0.60
    âĶģ
    -0.60
    omorphic
    -0.60
    hang
    -0.59
    ãĥĥ
    -0.58
     Fathers
    -0.57
    POSITIVE LOGITS
    EED
    1.45
    OIL
    1.33
    ORTS
    1.27
    ORT
    1.25
    ECT
    1.18
    ONSORED
    1.17
    IR
    1.04
    ERSON
    1.04
    ELL
    1.02
    LC
    1.02
    Activations Density 0.021%

    No Known Activations