© 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. 2-RES-JB
    11. 8342
    Prev
    Next
    INDEX
    Explanations

    mentions of mobile applications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific application or software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Halls
    -0.72
    terday
    -0.72
     Deity
    -0.68
    theless
    -0.65
    EngineDebug
    -0.64
     Roads
    -0.64
    noon
    -0.64
    cellaneous
    -0.61
    ãģį
    -0.59
    Ń·
    -0.59
    POSITIVE LOGITS
    alach
    1.15
    ortion
    1.08
    rehens
    0.95
    ointment
    0.93
    ropri
    0.92
    legate
    0.92
    earance
    0.91
    reciation
    0.91
    anooga
    0.89
    ucc
    0.83
    Activations Density 0.026%

    No Known Activations