© 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. 24048
    Prev
    Next
    INDEX
    Explanations

    negative terms related to language and communication, like inflammatory rhetoric, tones with evil connotations, and arrogant language

    oai_token-act-pair · gpt-3.5-turbo

    critical and negative language regarding societal issues and individuals

    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
    CCC
    -0.72
    input
    -0.64
    Local
    -0.61
    asus
    -0.60
     Federation
    -0.59
     Regions
    -0.59
     Fein
    -0.59
    ESE
    -0.58
     CIS
    -0.58
    relevant
    -0.57
    POSITIVE LOGITS
     notwithstanding
    1.10
     belie
    1.01
     overshadow
    0.98
     contrasted
    0.97
     shines
    0.96
     inspires
    0.94
     culminated
    0.91
     shone
    0.90
     manifests
    0.89
    fulness
    0.89
    Activations Density 0.227%

    No Known Activations