© 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. 6-RES-JB
    11. 17051
    Prev
    Next
    INDEX
    Explanations

    phrases indicating that something is incorrect or flawed

    oai_token-act-pair · gpt-3.5-turbo

    phrases questioning the existence of problems or issues

    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
    NetMessage
    -0.74
    minist
    -0.70
    ILA
    -0.70
     corrid
    -0.69
    pole
    -0.68
     Flavoring
    -0.67
    cit
    -0.66
    itation
    -0.64
    é¾
    -0.64
    chet
    -0.64
    POSITIVE LOGITS
    eous
    0.81
    fully
    0.80
    headed
    0.69
    lihood
    0.68
    align
    0.68
    î
    0.65
    ful
    0.64
     unfocusedRange
    0.63
     Libyan
    0.63
     wrong
    0.62
    Activations Density 0.022%

    No Known Activations