© 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. 3696
    Prev
    Next
    INDEX
    Explanations

    mention of public health issues or government policies related to health

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate recommendations or agreements in various contexts

    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
    ¬¼
    -0.79
    ocl
    -0.74
    NetMessage
    -0.71
    joy
    -0.68
    cel
    -0.68
    itialized
    -0.67
    ãĤ£
    -0.67
    itol
    -0.66
    *:
    -0.65
    ction
    -0.64
    POSITIVE LOGITS
     according
    1.15
     respectively
    0.92
     says
    0.87
     said
    0.84
     citing
    0.83
     prompting
    0.81
     POLITICO
    0.81
     including
    0.81
    ',"
    0.79
    said
    0.79
    Activations Density 0.481%

    No Known Activations