© 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. 9-RES-JB
    11. 4723
    Prev
    Next
    INDEX
    Explanations

    past tense verbs ending in 'ed'

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating processes and explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    this
    -0.67
    dule
    -0.67
    gdala
    -0.66
     thereto
    -0.62
     Commands
    -0.58
    osal
    -0.57
    rament
    -0.56
    ngth
    -0.56
     thereof
    -0.55
    ['
    -0.55
    POSITIVE LOGITS
     however
    0.69
     contrasted
    0.66
     incidentally
    0.66
     coupled
    0.65
     Firstly
    0.63
     Qiao
    0.62
     compounded
    0.62
    ilst
    0.61
     Lys
    0.60
     princ
    0.59
    Activations Density 0.476%

    No Known Activations