© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6387
    Prev
    Next
    INDEX
    Explanations

    words related to remodeling or renovation

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and words related to overwhelming experiences or feelings

    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
     watershed
    -0.63
     anth
    -0.62
     feast
    -0.58
     pref
    -0.57
     rec
    -0.56
     offences
    -0.56
     benefit
    -0.56
     exploits
    -0.56
     util
    -0.55
     suicide
    -0.55
    POSITIVE LOGITS
    eling
    4.43
    eled
    2.75
    els
    2.32
    elling
    2.10
    ELS
    1.79
    elled
    1.72
    elin
    1.53
    el
    1.50
    eln
    1.27
    EL
    1.20
    Activations Density 0.012%

    No Known Activations