INDEX

Explanations

proper nouns and specific phrases related to locations or institutions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "OK"

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

craft

-0.73

omorphic

-0.70

minecraft

-0.68

 brim

-0.67

clud

-0.66

oidal

-0.66

istics

-0.66

riber

-0.65

dimension

-0.65

bent

-0.65

POSITIVE LOGITS

AY

1.23

lahoma

1.16

awaru

0.92

YA

0.82

OK

0.79

WARD

0.77

ALLY

0.74

ESCO

0.72

SW

0.70

ANE

0.69

Activations Density 0.013%

proper nouns and specific phrases related to locations or institutions

instances of the word "OK"

No Comments

No Known Activations