© 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. 6-RES-JB
    11. 9879
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to expressing something in a straightforward or direct manner

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating blunt or straightforward communication

    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
    estic
    -0.78
    ilver
    -0.71
    atile
    -0.66
    Pg
    -0.65
    ivery
    -0.65
    olin
    -0.63
    ettings
    -0.63
    strom
    -0.63
    arnaev
    -0.62
    iliated
    -0.62
    POSITIVE LOGITS
     hypot
    0.98
     analogy
    0.90
     suffice
    0.87
     nutshell
    0.86
     guess
    0.80
     bluntly
    0.78
     anecd
    0.77
     metaphor
    0.77
    facts
    0.77
     suppose
    0.73
    Activations Density 0.684%

    No Known Activations