© 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. 8-RES-JB
    11. 3118
    Prev
    Next
    INDEX
    Explanations

    information related to locations or places, especially towns and cities

    oai_token-act-pair · gpt-3.5-turbo

    locations and geographic features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ))))
    -0.78
    )))
    -0.74
    )?
    -0.70
    ?ãĢį
    -0.64
    ?).
    -0.64
     }}
    -0.62
     persists
    -0.59
     discriminate
    -0.58
     prey
    -0.58
    etheless
    -0.57
    POSITIVE LOGITS
    ibrary
    0.70
    ipl
    0.65
     Catal
    0.64
     Ples
    0.63
    quart
    0.62
     Quart
    0.61
     whereas
    0.59
     (#
    0.58
     Instruments
    0.57
     Proced
    0.56
    Activations Density 1.265%

    No Known Activations