Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 8567
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal actions and decisions

    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
    hran
    -0.51
    appiness
    -0.49
     \'
    -0.48
    hra
    -0.48
    adh
    -0.47
    leep
    -0.46
    reath
    -0.46
    sg
    -0.46
    Crime
    -0.46
    natureconservancy
    -0.46
    POSITIVE LOGITS
     similarly
    1.07
     likewise
    1.01
    etheless
    0.99
     thereafter
    0.96
     additionally
    0.86
    anwhile
    0.82
     subsequently
    0.79
     curiously
    0.79
     downright
    0.78
     decidedly
    0.77
    Activations Density 1.708%

    No Known Activations