INDEX

Explanations

numerical figures, symbols, and formatting elements in text

oai_token-act-pair · gpt-3.5-turbo

text segments with special characters or formatting symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

seless

-0.77

acles

-0.75

 fireplace

-0.74

ahime

-0.73

inator

-0.71

unia

-0.70

 Beir

-0.69

nesses

-0.68

anse

-0.68

liness

-0.64

POSITIVE LOGITS

(*

0.81

(*

0.79

ERROR

0.76

STD

0.74

STDOUT

0.73

testing

0.73

TEXT

0.71

catentry

0.70

Thompson

0.69

FREE

0.69

Activations Density 0.025%

numerical figures, symbols, and formatting elements in text

text segments with special characters or formatting symbols

No Comments

No Known Activations