© 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. 7-RES-JB
    11. 15704
    Prev
    Next
    INDEX
    Explanations

    sequences of words related to actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of risk-taking behavior and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FIFA
    -0.57
     Riot
    -0.52
    âĢİ
    -0.51
     Khe
    -0.50
    <|endoftext|>
    -0.50
    posts
    -0.49
     welcome
    -0.49
    Joined
    -0.49
     acronym
    -0.49
     Tah
    -0.49
    POSITIVE LOGITS
    versely
    0.72
    etheless
    0.70
    essor
    0.67
    ovie
    0.67
    alogue
    0.65
    amina
    0.65
    oother
    0.64
    osite
    0.62
    orius
    0.62
    eele
    0.60
    Activations Density 0.910%

    No Known Activations