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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 5234
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial situations and consequences

    oai_token-act-pair · gpt-3.5-turbo

    negative or critical statements about various topics

    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
    REDACTED
    -0.67
    osure
    -0.59
     nutshell
    -0.59
    WER
    -0.52
    atus
    -0.51
    soDeliveryDate
    -0.50
    ¬¼
    -0.50
     retrospect
    -0.50
    ural
    -0.50
    endum
    -0.50
    POSITIVE LOGITS
     whereas
    0.78
    often
    0.74
     Conversely
    0.69
    selves
    0.64
     Especially
    0.63
     regardless
    0.63
     irrespective
    0.63
     They
    0.63
     moreover
    0.62
     beware
    0.62
    Activations Density 0.804%

    No Known Activations