INDEX

Explanations

words related to validity and authentication

oai_token-act-pair · gpt-3.5-turbo

expressions related to validation or legitimacy

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

hedon

-0.82

xual

-0.77

Mania

-0.71

irez

-0.68

 Grove

-0.66

mania

-0.65

Kut

-0.65

ynthesis

-0.64

hell

-0.64

opsy

-0.64

POSITIVE LOGITS

ators

1.08

ating

1.08

ator

0.98

alties

0.90

ates

0.87

ations

0.87

iation

0.78

acies

0.78

ifiers

0.77

itable

0.75

Activations Density 0.017%

words related to validity and authentication

expressions related to validation or legitimacy

No Comments

No Known Activations