© 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. 9-RES-JB
    11. 1525
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific goal or aim

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to objectives and intentions

    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
     cursing
    -0.63
     unequ
    -0.63
    Enough
    -0.59
     nick
    -0.58
     jaws
    -0.58
     unreliable
    -0.58
     acidic
    -0.57
    uffed
    -0.57
    liv
    -0.57
     shred
    -0.53
    POSITIVE LOGITS
     is
    0.87
     Goal
    0.82
    nings
    0.81
     goal
    0.79
     was
    0.79
    Goal
    0.77
    goal
    0.74
    çīĪ
    0.71
     takeaway
    0.70
    fore
    0.70
    Activations Density 0.167%

    No Known Activations