© 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. 14881
    Prev
    Next
    INDEX
    Explanations

    proper nouns commonly associated with specific attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating what entities or individuals are known for

    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
    soever
    -0.70
    atron
    -0.69
    down
    -0.64
    eth
    -0.64
    VR
    -0.63
    Enabled
    -0.61
    OTAL
    -0.60
    adr
    -0.59
    MRI
    -0.59
    risis
    -0.59
    POSITIVE LOGITS
    geries
    1.03
    bidden
    0.93
    gery
    0.89
     daring
    0.75
     having
    0.72
     producing
    0.70
    ked
    0.69
     frequent
    0.69
     cracking
    0.67
    ays
    0.67
    Activations Density 0.069%

    No Known Activations