INDEX

Explanations

technical terms related to specific topics like radiation, servers, and investigations

oai_token-act-pair · gpt-3.5-turbo

terms related to nuclear energy and disaster scenarios

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Router

-0.66

 Parenthood

-0.66

 Aires

-0.63

ãĤ¨ãĥ«

-0.62

 "$:/

-0.61

"{

-0.59

 cumbers

-0.57

 externalToEVAOnly

-0.57

 peak

-0.56

 Ariel

-0.55

POSITIVE LOGITS

_-_

1.13

/)

1.09

"}

0.98

_(

0.98

arthed

0.92

"},{"

0.91

__

0.89

/?

0.88

/#

0.84

Activations Density 0.094%

technical terms related to specific topics like radiation, servers, and investigations

terms related to nuclear energy and disaster scenarios

No Comments

No Known Activations