© 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. 13572
    Prev
    Next
    INDEX
    Explanations

    phrases related to absorption or substances being absorbed

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the process of absorption in various contexts

    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
    FTWARE
    -0.64
    eways
    -0.63
    perm
    -0.62
     exoner
    -0.60
     Gemini
    -0.59
    Egypt
    -0.57
    eq
    -0.57
    ;;;;;;;;;;;;
    -0.56
    say
    -0.55
     Investigator
    -0.55
    POSITIVE LOGITS
     absorbs
    0.89
    ibles
    0.88
    ency
    0.84
    encies
    0.84
     absorbing
    0.84
     absorbed
    0.80
    uates
    0.79
    atform
    0.79
    iencies
    0.77
    ptive
    0.76
    Activations Density 0.037%

    No Known Activations