© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 4149
    Prev
    Next
    INDEX
    Explanations

    words related to injustice or criticism

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "un-" indicating negation or reversal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pound
    -0.84
     briefs
    -0.78
     Grayson
    -0.78
     Fields
    -0.78
     Peb
    -0.74
     Tackle
    -0.72
     Ples
    -0.72
     Elements
    -0.72
    hetti
    -0.70
     Sut
    -0.69
    POSITIVE LOGITS
    fortunately
    1.28
    iversity
    1.21
    usual
    1.17
    likely
    1.14
    employment
    1.14
    animous
    1.13
    expected
    1.10
    readable
    1.09
    cles
    1.07
    ruly
    1.07
    Activations Density 0.018%

    No Known Activations