© 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. 9899
    Prev
    Next
    INDEX
    Explanations

    personal pronouns combined with present tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty and personal feelings

    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
    Often
    -0.72
    sequently
    -0.72
    env
    -0.71
    etheless
    -0.71
     Historically
    -0.69
    versely
    -0.68
    Generally
    -0.68
    Initially
    -0.68
    ilst
    -0.68
    soever
    -0.67
    POSITIVE LOGITS
     gonna
    1.03
     fuckin
    0.83
    !'"
    0.81
    eeee
    0.80
     fucked
    0.80
     fucking
    0.80
    !'
    0.79
    yy
    0.77
     gotta
    0.75
     filthy
    0.75
    Activations Density 0.494%

    No Known Activations