INDEX

Explanations

phrases related to proven facts or established truths

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "proven" and its variations, indicating evidence or validation of 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

alon

-0.75

eeper

-0.72

utterstock

-0.71

 Shoes

-0.70

regate

-0.65

adish

-0.65

querade

-0.64

umbn

-0.64

onew

-0.64

IDES

-0.64

POSITIVE LOGITS

iary

1.05

 proven

0.90

iferation

0.84

 è£ıè

0.74

 debunked

0.73

icity

0.71

 factual

0.69

âĵĺ

0.68

uable

0.68

icist

0.68

Activations Density 0.064%

phrases related to proven facts or established truths

occurrences of the word "proven" and its variations, indicating evidence or validation of claims

No Comments

No Known Activations