© 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. 4-RES-JB
    11. 16075
    Prev
    Next
    INDEX
    Explanations

    locations or specific settings within a larger space, particularly rooms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "room" in various contexts

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

    No Comments

    Negative Logits
    HER
    -0.66
     Iss
    -0.64
     Uz
    -0.64
     retribution
    -0.61
    pend
    -0.61
     Garc
    -0.59
     Accessed
    -0.59
     Enforcement
    -0.58
    NECT
    -0.58
    JUST
    -0.58
    POSITIVE LOGITS
    room
    1.18
     room
    0.97
     rooms
    0.96
    rooms
    0.96
     doors
    0.91
     upstairs
    0.86
     Room
    0.84
    lain
    0.83
    itory
    0.83
    Room
    0.82
    Activations Density 0.020%

    No Known Activations