© 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. 2-RES-JB
    11. 9253
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Aber" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the location Abercynon and its associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jackets
    -0.70
    è£ħ
    -0.66
     Bubble
    -0.65
     pity
    -0.65
    stanbul
    -0.65
    ODUCT
    -0.61
    onics
    -0.61
     Chapman
    -0.61
    knife
    -0.61
    owder
    -0.60
    POSITIVE LOGITS
    ration
    1.04
    rations
    0.93
    rative
    0.91
     Aber
    0.87
    rant
    0.86
    rational
    0.85
    keyes
    0.80
    terior
    0.78
    rants
    0.78
    allel
    0.78
    Activations Density 0.016%

    No Known Activations