© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3058
    Prev
    Next
    INDEX
    Explanations

    instances where actions or decisions are being directed towards a specific goal or outcome

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "put"

    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
    externalActionCode
    -0.98
    ording
    -0.66
    riott
    -0.66
     Examiner
    -0.65
     Austral
    -0.65
    uary
    -0.62
    yan
    -0.62
    cean
    -0.61
     Sample
    -0.60
    BLE
    -0.59
    POSITIVE LOGITS
    rid
    0.91
    ongh
    0.90
     together
    0.90
     forth
    0.88
    tering
    0.87
    downs
    0.84
    tin
    0.83
     aside
    0.81
    down
    0.80
    tered
    0.77
    Activations Density 0.047%

    No Known Activations