© 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. 3-RES-JB
    6. 8350
    Prev
    Next
    INDEX
    Explanations

    references to different blocks or locations in a city

    oai_token-act-pair · gpt-3.5-turbo

    numerical addresses and location descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maths
    -0.96
     scept
    -0.92
     learnt
    -0.88
    ploma
    -0.86
     epigen
    -0.84
     mould
    -0.83
     autobi
    -0.83
     philosopher
    -0.83
     physicist
    -0.83
     rapport
    -0.82
    POSITIVE LOGITS
     Avenue
    1.15
     sidewalks
    1.06
     Parking
    1.05
     Interstate
    1.03
     Parkway
    1.03
     Boulevard
    1.03
     Downtown
    1.03
     downtown
    1.02
     Recreation
    1.00
     sidewalk
    1.00
    Activations Density 0.990%

    No Known Activations