© 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. 8-RES-JB
    11. 6896
    Prev
    Next
    INDEX
    Explanations

    proper nouns denoting individuals or organizations with biographical information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" indicating past actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lag
    -0.79
     Extend
    -0.77
     slideshow
    -0.74
    ologies
    -0.72
     Which
    -0.69
     Needs
    -0.66
    izable
    -0.65
    ological
    -0.65
     HAVE
    -0.65
     Formation
    -0.64
    POSITIVE LOGITS
     born
    1.30
     able
    1.17
     diagnosed
    1.08
     unable
    1.06
     arrested
    1.03
     sentenced
    1.02
     assassinated
    1.01
     instrumental
    1.01
     appointed
    1.00
     married
    1.00
    Activations Density 0.261%

    No Known Activations