© 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. 8-RES-JB
    11. 6959
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulations, laws, and actions

    oai_token-act-pair · gpt-3.5-turbo

    collective nouns and terms related to groups or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edia
    -0.75
    tch
    -0.70
    ahime
    -0.68
    eele
    -0.66
    resy
    -0.66
    senal
    -0.63
    odcast
    -0.61
    uristic
    -0.61
    eka
    -0.61
    agram
    -0.60
    POSITIVE LOGITS
     except
    1.71
    except
    1.26
     alike
    1.13
     whatsoever
    1.05
     irrespective
    1.04
    soever
    1.04
     imaginable
    1.04
     regardless
    0.94
     thereafter
    0.88
     equally
    0.84
    Activations Density 0.338%

    No Known Activations