© 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. 3-RES-JB
    11. 8220
    Prev
    Next
    INDEX
    Explanations

    phrases related to announcements or statements

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating the presence or actions related to various subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onlook
    -0.74
    economic
    -0.74
     Chero
    -0.67
     inexper
    -0.65
    illions
    -0.64
    iating
    -0.63
    sequent
    -0.63
    ecd
    -0.61
     abstraction
    -0.61
    iates
    -0.60
    POSITIVE LOGITS
    senal
    0.96
    ©¶æ
    0.72
    cussion
    0.70
     pleased
    0.69
     hereby
    0.68
     SERV
    0.67
     Mahjong
    0.66
     Editor
    0.66
    20439
    0.65
    IDER
    0.65
    Activations Density 0.705%

    No Known Activations