© 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. 7-RES-JB
    11. 21424
    Prev
    Next
    INDEX
    Explanations

    brand names or specific terms within a larger context

    oai_token-act-pair · gpt-3.5-turbo

    specific organizations, entities, and health-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htaking
    -0.66
    ministic
    -0.66
    byss
    -0.60
    Availability
    -0.59
     ().
    -0.57
     Pwr
    -0.57
    ospons
    -0.56
     Trace
    -0.55
    galitarian
    -0.55
     Curious
    -0.55
    POSITIVE LOGITS
    ]"
    2.17
    ]
    2.08
    ]."
    1.96
    ],"
    1.96
    ]'
    1.87
    ],
    1.79
    ']
    1.75
    ?]
    1.64
    ].
    1.62
    ]-
    1.61
    Activations Density 0.150%

    No Known Activations