© 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. 14069
    Prev
    Next
    INDEX
    Explanations

    mentions of names and titles associated with news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and figures in news articles

    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
    SPONSORED
    -0.85
    Newsletter
    -0.84
     Secondly
    -0.79
    Secondly
    -0.73
    }.
    -0.71
     assum
    -0.69
    :,
    -0.68
    phasis
    -0.66
    åĤ
    -0.65
    ↵Âł
    -0.64
    POSITIVE LOGITS
     watchdog
    0.70
    "))
    0.70
     POLITICO
    0.68
     bicycl
    0.68
    zbollah
    0.65
    odcast
    0.63
    heed
    0.62
    reetings
    0.62
     constitu
    0.61
     Latest
    0.61
    Activations Density 0.740%

    No Known Activations