Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3525
    Prev
    Next
    INDEX
    Explanations

    elements related to programming languages, such as specific syntax and keywords

    oai_token-act-pair · gpt-3.5-turbo

    elements related to programming syntax or data structures

    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
     nostalg
    -0.66
     hindsight
    -0.63
     understatement
    -0.56
     metaphor
    -0.56
     typew
    -0.55
     Negro
    -0.54
     slang
    -0.54
    uristic
    -0.53
     of
    -0.53
     euphem
    -0.53
    POSITIVE LOGITS
    itals
    0.71
    emies
    0.60
    >>
    0.59
     respectively
    0.58
    Li
    0.58
    cludes
    0.55
    urities
    0.52
    Further
    0.52
    alk
    0.51
    >>>
    0.49
    Activations Density 0.902%

    No Known Activations