INDEX

Explanations

references to or mentions of automobiles

oai_token-act-pair · gpt-3.5-turbo

mentions of cars and related terminology

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Flavoring

-1.03

 Seym

-0.82

enance

-0.77

ãĥĥãĥĪ

-0.76

iversal

-0.73

tle

-0.72

edIn

-0.71

é¾įå¥ĳå£«

-0.71

vironment

-0.70

 Subtle

-0.70

POSITIVE LOGITS

ousel

1.55

riages

1.30

penter

1.30

rera

1.16

olina

1.04

riage

1.00

negie

0.97

riers

0.94

 dealership

0.93

acter

0.91

Activations Density 0.036%

references to or mentions of automobiles

mentions of cars and related terminology

No Comments

No Known Activations