© 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. 0-RES-JB
    11. 23198
    Prev
    Next
    INDEX
    Explanations

    words related to legal or financial circumstances, such as 'bankruptcy' and 'disrupters'

    oai_token-act-pair · gpt-3.5-turbo

    words related to disruption or interruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cast
    -0.62
     Spl
    -0.62
     Kill
    -0.61
    å½
    -0.61
     demographics
    -0.60
     html
    -0.59
     Teen
    -0.58
     already
    -0.58
     formatted
    -0.58
     bec
    -0.58
    POSITIVE LOGITS
    rup
    4.91
    rupulous
    1.43
    rupt
    1.18
    rop
    1.15
    combe
    1.12
    ru
    1.08
    razen
    1.05
    rip
    0.99
    rig
    0.95
    rophe
    0.95
    Activations Density 0.020%

    No Known Activations