© 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. 4-RES-JB
    11. 18375
    Prev
    Next
    INDEX
    Explanations

    terms related to providing or receiving various forms of assistance or support

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of assistance or aid

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

    No Comments

    Negative Logits
    aval
    -0.81
    bish
    -0.73
    Benz
    -0.71
    steel
    -0.71
    LINE
    -0.68
     Hebdo
    -0.68
    Compar
    -0.67
    nen
    -0.67
     Beard
    -0.66
    ross
    -0.66
    POSITIVE LOGITS
     assistance
    0.99
    enza
    0.88
     aid
    0.84
    ateral
    0.80
     recip
    0.79
     recipients
    0.78
     Assistance
    0.77
    ilitation
    0.76
     assisting
    0.74
     counselor
    0.73
    Activations Density 0.010%

    No Known Activations