INDEX

Explanations

key themes or components within a larger piece of writing

oai_token-act-pair · gpt-3.5-turbo

phrases related to key components or elements within various contexts

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

lez

-0.75

oped

-0.72

ulus

-0.70

athon

-0.69

raid

-0.68

esi

-0.66

umbo

-0.65

tor

-0.64

gee

-0.64

essed

-0.64

POSITIVE LOGITS

 thereof

0.90

 elements

0.89

 aspects

0.85

afety

0.84

etting

0.81

mith

0.80

omething

0.79

 components

0.78

etter

0.78

 resembling

0.77

Activations Density 0.111%

key themes or components within a larger piece of writing

phrases related to key components or elements within various contexts

No Comments

No Known Activations