© 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. 2-RES-JB
    11. 13456
    Prev
    Next
    INDEX
    Explanations

    words related to things that are impenetrable

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of barriers and their permiability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    croft
    -0.83
    e
    -0.74
    Accessory
    -0.71
     concession
    -0.70
    ĺħ
    -0.70
     confession
    -0.67
    Ĥ¬
    -0.66
    conn
    -0.65
    hold
    -0.64
     Tonight
    -0.63
    POSITIVE LOGITS
    etr
    1.40
    agonal
    1.06
    agnetic
    1.03
    agog
    1.03
    aining
    1.01
    ading
    1.00
    ansky
    0.97
    acer
    0.96
    asso
    0.95
    asures
    0.95
    Activations Density 0.008%

    No Known Activations