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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 10649
    Prev
    Next
    INDEX
    Explanations

    phrases related to group activities or actions

    oai_token-act-pair · gpt-3.5-turbo

    words indicating collective experiences or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     priesthood
    -0.71
    clus
    -0.65
    egal
    -0.63
     pole
    -0.61
     brim
    -0.61
    rums
    -0.61
     epid
    -0.60
     cycl
    -0.59
     gener
    -0.59
    ennial
    -0.59
    POSITIVE LOGITS
     Needs
    0.89
    body
    0.89
    Else
    0.83
     Else
    0.83
     Dreams
    0.82
     Advice
    0.80
     Files
    0.79
     Emails
    0.76
     Called
    0.76
     Basics
    0.75
    Activations Density 0.056%

    No Known Activations