INDEX

Explanations

symbols or symbolic representations

oai_token-act-pair · gpt-3.5-turbo

words that denote symbols or symbolic representations

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

 Oaks

-0.66

isode

-0.65

 oats

-0.63

cker

-0.63

ieri

-0.62

ULTS

-0.62

 Lank

-0.60

alsh

-0.59

SOURCE

-0.59

 Grave

-0.58

POSITIVE LOGITS

ically

1.02

izes

0.93

ized

0.90

 symbols

0.88

icons

0.83

 Meaning

0.83

hips

0.82

 symbol

0.82

istically

0.81

izing

0.81

Activations Density 0.021%

symbols or symbolic representations

words that denote symbols or symbolic representations

No Comments

No Known Activations