© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 12367
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Habitat" followed by a number or word indicating a certain characteristic or action related to habitat

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific burger chain and related habitat conservation themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enthal
    -0.86
    esses
    -0.85
    istry
    -0.85
    ifact
    -0.78
    ising
    -0.76
    krit
    -0.75
    smith
    -0.75
    ocrine
    -0.74
    inness
    -0.72
    esters
    -0.72
    POSITIVE LOGITS
     retri
    0.72
     deprivation
    0.70
    ibilities
    0.68
    rador
    0.66
    Sov
    0.66
    rers
    0.64
    ¢
    0.63
    ABLE
    0.63
    ttes
    0.62
    ã
    0.62
    Activations Density 0.085%

    No Known Activations