© 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. 6-RES-JB
    11. 4302
    Prev
    Next
    INDEX
    Explanations

    specific places or contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or contexts associated with the word "inside."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onna
    -0.72
    phasis
    -0.72
    folk
    -0.71
    pleting
    -0.71
    staking
    -0.71
    arcity
    -0.71
    llor
    -0.70
    sels
    -0.67
    aintain
    -0.65
    arily
    -0.65
    POSITIVE LOGITS
     bounds
    1.16
     confines
    1.02
     walls
    1.00
     perimeter
    0.90
     boundaries
    0.85
     gates
    0.85
     bubble
    0.85
    âĸ¬
    0.85
     doors
    0.84
     limits
    0.81
    Activations Density 0.119%

    No Known Activations