© 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. 11-RES-JB
    11. 15761
    Prev
    Next
    INDEX
    Explanations

    places or locations, particularly focusing on specific locations that include the structure type and/or city name

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hower
    -0.69
    kamp
    -0.64
     DOI
    -0.63
    staking
    -0.61
    Hack
    -0.60
     DeL
    -0.60
     date
    -0.58
    éĹĺ
    -0.56
     Clown
    -0.56
    è£ħ
    -0.55
    POSITIVE LOGITS
    ilda
    0.81
    roma
    0.66
    eches
    0.65
    obia
    0.64
    opus
    0.61
    iour
    0.61
    eret
    0.60
    arten
    0.60
    arde
    0.60
    orst
    0.58
    Activations Density 0.136%

    No Known Activations