© 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. 8-RES-JB
    11. 3450
    Prev
    Next
    INDEX
    Explanations

    words with the substring 'bl'

    oai_token-act-pair · gpt-3.5-turbo

    words starting with "bl" that suggest negative connotations or actions

    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
    Construct
    -0.81
    geist
    -0.71
    AGE
    -0.71
    UAL
    -0.69
    RAL
    -0.68
    ETF
    -0.67
    ÃįÃį
    -0.66
    XY
    -0.66
    AGES
    -0.66
    Pg
    -0.65
    POSITIVE LOGITS
    ossom
    1.31
    izzard
    1.17
    ameless
    1.11
    adders
    1.05
    anche
    1.05
    itzer
    1.05
    oop
    1.05
    anks
    1.02
    unders
    1.01
    anches
    1.00
    Activations Density 0.014%

    No Known Activations