© 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. 2-RES-JB
    11. 12828
    Prev
    Next
    INDEX
    Explanations

    truncated words or parts of words

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with fragility and fatigue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    payer
    -0.82
    eers
    -0.77
    atari
    -0.75
    RAFT
    -0.68
     Bundy
    -0.68
    rouse
    -0.67
    rieving
    -0.66
    rooms
    -0.65
    rieve
    -0.64
    ribute
    -0.64
    POSITIVE LOGITS
     Fra
    1.16
    Fra
    0.98
    zzle
    0.94
     encount
    0.87
    zz
    0.87
    udge
    0.83
    viation
    0.81
    ï¸
    0.78
    iture
    0.75
    ilty
    0.71
    Activations Density 0.007%

    No Known Activations