© 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. 3-RES-JB
    11. 10682
    Prev
    Next
    INDEX
    Explanations

    mentions of the location or origin of entities or activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating geographical locations followed by the word "based."

    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
    osen
    -0.79
    dimension
    -0.77
    200000
    -0.75
    éŃĶ
    -0.74
    arthy
    -0.72
    Balt
    -0.70
    osure
    -0.69
    о
    -0.68
    OSE
    -0.67
    older
    -0.67
    POSITIVE LOGITS
    quartered
    0.93
     activist
    0.72
     contingent
    0.70
     operator
    0.69
    undo
    0.68
     execut
    0.67
     headquartered
    0.66
     entrepreneur
    0.65
     cooperative
    0.65
    recy
    0.64
    Activations Density 0.024%

    No Known Activations