© 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. 10-RES-JB
    11. 17375
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs indicating action

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to groups of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.74
     RTX
    -0.65
    ãĥ¼ãĥĨ
    -0.63
    Correct
    -0.62
    00000
    -0.61
    =-=-
    -0.60
    rium
    -0.59
    bridge
    -0.58
    Press
    -0.58
    politics
    -0.58
    POSITIVE LOGITS
     were
    1.00
     are
    0.98
     perished
    0.92
     relate
    0.84
     belong
    0.84
     involve
    0.82
     consisted
    0.81
     originated
    0.81
     reside
    0.81
     have
    0.77
    Activations Density 0.072%

    No Known Activations