INDEX

Explanations

symbols or symbolic representations

oai_token-act-pair · gpt-3.5-turbo

references to symbols and their meanings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Oaks

-0.66

amina

-0.66

 Lank

-0.64

SOURCE

-0.63

Bed

-0.61

 Brewers

-0.61

alsh

-0.61

 Bucks

-0.61

erity

-0.61

 Packers

-0.60

POSITIVE LOGITS

 symbols

0.99

 symbol

0.95

ically

0.93

ized

0.89

mbol

0.89

 Meaning

0.89

matically

0.88

izes

0.87

lia

0.85

icons

0.85

Activations Density 0.022%

symbols or symbolic representations

references to symbols and their meanings

No Comments

No Known Activations