© 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. 4-RES-JB
    11. 11197
    Prev
    Next
    INDEX
    Explanations

    words related to being impenetrable or barriers

    oai_token-act-pair · gpt-3.5-turbo

    words related to barriers and boundaries

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

    No Comments

    Negative Logits
    Ĥ¬
    -0.78
    croft
    -0.78
    conn
    -0.74
    e
    -0.74
    ĺħ
    -0.72
    Accessory
    -0.71
    eur
    -0.68
     Dragonbound
    -0.65
     Hastings
    -0.65
    corn
    -0.64
    POSITIVE LOGITS
    etr
    1.17
    aining
    1.11
    agonal
    1.05
    ading
    1.02
    abulary
    1.01
    acer
    0.97
    agnetic
    0.96
    ansky
    0.96
    ission
    0.96
    aded
    0.95
    Activations Density 0.013%

    No Known Activations