INDEX

Explanations

comparisons between objects or entities

oai_token-act-pair · gpt-3.5-turbo

words related to resemblance or similarity

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

ourse

-0.79

alloc

-0.78

imb

-0.75

arta

-0.71

FT

-0.71

load

-0.70

alt

-0.70

gard

-0.69

mouth

-0.69

deal

-0.69

POSITIVE LOGITS

lihood

1.71

lier

0.94

liest

0.85

 likeness

0.82

 ours

0.81

liness

0.78

awei

0.73

 resembling

0.72

 lifeless

0.71

 theirs

0.70

Activations Density 0.032%

comparisons between objects or entities

words related to resemblance or similarity

No Comments

No Known Activations