© 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. 7-RES-JB
    11. 16807
    Prev
    Next
    INDEX
    Explanations

    phrases related to positions or locations within a sequence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time or transitions within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.74
     namely
    -0.73
     listened
    -0.71
     msec
    -0.70
    note
    -0.70
     reprinted
    -0.67
    soever
    -0.67
     accompanied
    -0.67
     accordingly
    -0.66
    among
    -0.66
    POSITIVE LOGITS
     end
    1.08
     goal
    1.04
     conclusion
    1.00
     horizon
    0.97
     extremes
    0.96
     completion
    0.95
     goals
    0.93
     heights
    0.93
     forefront
    0.91
     endpoint
    0.89
    Activations Density 0.193%

    No Known Activations