© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 24048
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs in the base form

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express obligations, abilities, or expectations related to people

    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
     sugg
    -0.66
    acan
    -0.66
     Leviathan
    -0.66
    etheus
    -0.65
    cms
    -0.64
     pse
    -0.62
     Klu
    -0.62
    ibrary
    -0.61
    berra
    -0.61
     HG
    -0.61
    POSITIVE LOGITS
     unus
    0.67
    ãĥĩãĤ£
    0.64
     richer
    0.61
    MON
    0.61
    tu
    0.60
    ãĥģ
    0.60
     inher
    0.59
    bye
    0.58
     goodbye
    0.57
     TAMADRA
    0.57
    Activations Density 0.178%

    No Known Activations