© 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. 11-RES-JB
    11. 22625
    Prev
    Next
    INDEX
    Explanations

    negative or cautionary statements regarding political or societal issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political activism and collective action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciating
    -0.84
     Checking
    -0.82
    audio
    -0.79
     suggestive
    -0.78
     researching
    -0.73
    Audio
    -0.73
    76561
    -0.72
     estimating
    -0.70
    checking
    -0.69
     annotations
    -0.69
    POSITIVE LOGITS
     perish
    1.55
     crumble
    1.44
     capit
    1.41
     revolt
    1.37
     starve
    1.36
     prevail
    1.33
     prosper
    1.33
     die
    1.32
     disband
    1.31
     succumb
    1.30
    Activations Density 0.330%

    No Known Activations