© 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. 4-RES-JB
    11. 14757
    Prev
    Next
    INDEX
    Explanations

    locations or places with spatial specificity

    oai_token-act-pair · gpt-3.5-turbo

    geographical references related to specific locations and regions

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

    No Comments

    Negative Logits
    Charges
    -0.72
     personally
    -0.69
    ealous
    -0.67
    PASS
    -0.66
    PLIED
    -0.65
    OFF
    -0.64
     Likes
    -0.64
    Own
    -0.63
    BuyableInstoreAndOnline
    -0.63
     invitations
    -0.63
    POSITIVE LOGITS
    insula
    0.88
    west
    0.88
     ridge
    0.81
     Caucasus
    0.81
     region
    0.79
     Appalach
    0.79
     inland
    0.78
     suburbs
    0.78
    east
    0.78
     valleys
    0.78
    Activations Density 0.193%

    No Known Activations