INDEX

Explanations

words related to exemplifying or embodying a concept or idea

oai_token-act-pair · gpt-3.5-turbo

terms related to examples and embodiment of concepts or ideals

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

 oats

-0.75

 trip

-0.65

cloth

-0.64

 hump

-0.63

interrupted

-0.63

hand

-0.63

vernment

-0.61

fetched

-0.61

 yield

-0.59

 efficiently

-0.58

POSITIVE LOGITS

orer

0.91

 exempl

0.89

rities

0.89

endor

0.84

arity

0.84

aris

0.81

ocrat

0.80

ographs

0.78

arious

0.78

arist

0.78

Activations Density 0.028%

words related to exemplifying or embodying a concept or idea

terms related to examples and embodiment of concepts or ideals

No Comments

No Known Activations