© 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. 0-RES-JB
    11. 4121
    Prev
    Next
    INDEX
    Explanations

    terms related to resistance or assistance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to assistance or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     restruct
    -0.63
     accounting
    -0.61
    IFF
    -0.60
     scr
    -0.59
     Alban
    -0.59
     envy
    -0.59
    VM
    -0.59
     empt
    -0.58
     summar
    -0.57
     cher
    -0.57
    POSITIVE LOGITS
    istance
    4.11
    istant
    2.15
     Resistance
    1.60
    kson
    1.30
    ources
    1.22
    ociation
    1.20
    peed
    1.18
    urrection
    1.14
    lihood
    1.10
    ensation
    1.10
    Activations Density 0.036%

    No Known Activations