INDEX

Explanations

phrases related to providing evidence or support for a statement

oai_token-act-pair · gpt-3.5-turbo

phrases related to supporting or validating statements or claims

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

avery

-0.86

adel

-0.75

mouth

-0.73

kie

-0.72

erve

-0.71

ities

-0.69

acht

-0.69

obs

-0.68

eteenth

-0.68

isha

-0.67

POSITIVE LOGITS

dates

0.78

 shaky

0.73

rating

0.72

packs

0.70

dating

0.70

stretched

0.69

EVs

0.68

 Rept

0.67

olicy

0.65

 against

0.64

Activations Density 0.020%

phrases related to providing evidence or support for a statement

phrases related to supporting or validating statements or claims

No Comments

No Known Activations