INDEX

Explanations

words related to reversing or undoing actions

oai_token-act-pair · gpt-3.5-turbo

phrases related to social or political changes

oai_token-act-pair · gpt-4o-mini Triggered 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

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

respond

-0.62

 Aware

-0.61

ebook

-0.59

assadors

-0.56

soDeliveryDate

-0.55

 compares

-0.54

hovah

-0.53

 reacts

-0.53

erity

-0.52

 Âł Âł Âł Âł Âł Âł Âł Âł

-0.52

POSITIVE LOGITS

 notion

0.76

 longstanding

0.75

 pree

0.75

 norm

0.74

 precon

0.73

 existing

0.72

 notions

0.72

 tradition

0.70

 traditional

0.69

 altogether

0.69

Activations Density 0.942%

words related to reversing or undoing actions

phrases related to social or political changes

No Comments

No Known Activations