INDEX

Explanations

phrases or sentences expressing the concept of "not always"

oai_token-act-pair · gpt-3.5-turbo

phrases indicating consistency or ongoing situations

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

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IDA

-0.80

bern

-0.77

pour

-0.72

externalActionCode

-0.72

zai

-0.72

bath

-0.72

hole

-0.70

Wad

-0.70

sonian

-0.70

workshop

-0.69

POSITIVE LOGITS

 bothered

0.87

 necessarily

0.86

 appre

0.84

entimes

0.79

 appreciated

0.78

 forg

0.77

 appe

0.75

 portrayed

0.75

 mistaken

0.74

theless

0.73

Activations Density 0.017%

phrases or sentences expressing the concept of "not always"

phrases indicating consistency or ongoing situations

No Comments

No Known Activations