INDEX

Explanations

phrases indicating a shift or continuation in the conversation

oai_token-act-pair · gpt-3.5-turbo

conditional phrases that imply a hypothetical situation or requirement

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

shown

-0.73

capt

-0.63

Interstitial

-0.61

AMA

-0.60

Tan

-0.60

DERR

-0.59

 PRESS

-0.58

aternal

-0.58

FN

-0.58

AGES

-0.56

POSITIVE LOGITS

aucus

0.99

endor

0.79

oiler

0.76

 congr

0.73

hew

0.73

ratulations

0.70

enos

0.69

iatus

0.66

ften

0.66

inki

0.61

Activations Density 0.120%

phrases indicating a shift or continuation in the conversation

conditional phrases that imply a hypothetical situation or requirement

No Comments

No Known Activations