© 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. 711
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific events or actions with a focus on present or recent activity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate important events or occurrences

    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
    @
    -0.84
     Recomm
    -0.73
    estate
    -0.71
    hof
    -0.69
    },{"
    -0.69
    Joined
    -0.68
    bol
    -0.68
    norm
    -0.66
    KY
    -0.66
    ]}
    -0.66
    POSITIVE LOGITS
     hindsight
    1.03
     exceptions
    0.88
     caveat
    0.80
     caveats
    0.79
     exception
    0.78
     emph
    0.75
     twist
    0.74
     gone
    0.69
     aster
    0.69
     bang
    0.69
    Activations Density 0.456%

    No Known Activations