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

    Neuronpedia

    Jacobian LensNEW
    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. 21134
    Prev
    Next
    INDEX
    Explanations

    phrases related to perseverance and resilience

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to struggle or conflict

    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
     guiActiveUn
    -0.93
    nostic
    -0.74
    ĸļ
    -0.68
    ADRA
    -0.68
    apore
    -0.67
    =-=-=-=-=-=-=-=-
    -0.66
    hower
    -0.66
    mbuds
    -0.66
    «ĺ
    -0.65
    atern
    -0.64
    POSITIVE LOGITS
     Bullets
    0.75
     abras
    0.73
     nails
    0.72
     weeds
    0.71
    nered
    0.70
     bruising
    0.67
     oats
    0.66
    ding
    0.63
     edges
    0.61
    ainment
    0.60
    Activations Density 0.110%

    No Known Activations