INDEX

Explanations

words related to locations or names

oai_token-act-pair · gpt-3.5-turbo

suffixes related to terms in politics or governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

elf

-0.78

olicy

-0.66

rieve

-0.65

é¾įå

-0.64

liness

-0.64

earance

-0.62

ĸļ

-0.61

Frameworks

-0.61

 Shack

-0.59

UTF

-0.59

POSITIVE LOGITS

ysis

1.20

pha

1.19

idad

1.07

ized

1.07

ogy

1.06

tarian

1.04

itÃ©

1.04

ities

1.04

icious

1.00

tarians

0.99

Activations Density 0.102%

words related to locations or names

suffixes related to terms in politics or governance

No Comments

No Known Activations