© 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. 10-RES-JB
    11. 20453
    Prev
    Next
    INDEX
    Explanations

    words related to specific geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    plurals and possessive forms related to geographical locations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASED
    -0.82
    ously
    -0.72
    Äĩ
    -0.72
    SIGN
    -0.71
    TI
    -0.71
    ILE
    -0.68
    efully
    -0.67
    osponsors
    -0.66
    eful
    -0.63
    RANT
    -0.62
    POSITIVE LOGITS
    boro
    1.45
    pring
    1.42
    bury
    1.31
    ville
    1.31
    mith
    1.29
    hire
    1.25
    borough
    1.24
    burg
    1.23
    dale
    1.22
    leeve
    1.16
    Activations Density 0.137%

    No Known Activations