INDEX

Explanations

images or phrases related to images

oai_token-act-pair · gpt-3.5-turbo

references to images in the text

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

cffff

-0.90

aptic

-0.84

hurst

-0.84

ategory

-0.83

itte

-0.82

ighter

-0.78

uckle

-0.78

woods

-0.76

kson

-0.76

odcast

-0.75

POSITIVE LOGITS

 galleries

0.98

gallery

0.96

 gallery

0.93

 caption

0.88

 images

0.86

img

0.84

 macros

0.84

 image

0.81

 Gallery

0.78

 depicting

0.78

Activations Density 0.040%

images or phrases related to images

references to images in the text

No Comments

No Known Activations