© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 18700
    Prev
    Next
    INDEX
    Explanations

    terms related to financial actions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and financial issues

    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
     rumours
    -0.61
     metre
    -0.59
     defences
    -0.58
     programmes
    -0.57
    rums
    -0.57
     civilisation
    -0.56
     rubbish
    -0.56
     humour
    -0.55
    ãĥ£
    -0.55
     favourite
    -0.53
    POSITIVE LOGITS
     nonetheless
    0.72
     anew
    0.71
     statewide
    0.69
     regardless
    0.69
     insofar
    0.66
     additionally
    0.66
     leveraging
    0.64
     again
    0.63
     culminating
    0.63
    .
    0.62
    Activations Density 0.885%

    No Known Activations