© 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. 7-RES-JB
    11. 24504
    Prev
    Next
    INDEX
    Explanations

    phrases related to releasing and launching products or updates

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to the launch or release of products and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.85
    sis
    -0.77
    etta
    -0.76
    sein
    -0.75
    hene
    -0.72
    ese
    -0.69
    otten
    -0.68
    cens
    -0.65
    ritical
    -0.65
    chan
    -0.64
    POSITIVE LOGITS
     refunds
    0.79
     prototypes
    0.78
     partnerships
    0.77
     alternatives
    0.75
     proprietary
    0.74
    senal
    0.74
     licences
    0.72
     DRAGON
    0.72
     products
    0.72
     CCTV
    0.71
    Activations Density 0.334%

    No Known Activations