Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18666
    Prev
    Next
    INDEX
    Explanations

    mentions of negative reactions or criticism towards a particular subject

    oai_token-act-pair · gpt-3.5-turbo

    instances of backlash or opposition to various actions or decisions

    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
    tein
    -0.90
    estones
    -0.84
    estone
    -0.82
    ogo
    -0.78
    ramer
    -0.75
    aple
    -0.73
    ramid
    -0.72
    uchin
    -0.70
    ilts
    -0.69
    teness
    -0.66
    POSITIVE LOGITS
     backlash
    1.17
    lash
    1.06
     retaliation
    0.82
     harshly
    0.81
     against
    0.81
     reaction
    0.80
     fury
    0.78
     reactions
    0.77
     retaliate
    0.77
     responses
    0.77
    Activations Density 0.008%

    No Known Activations