INDEX

Explanations

commands or functions related to reading and writing data in a computer program

oai_token-act-pair · gpt-3.5-turbo

terms related to writing and file operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

alian

-0.86

Ĭ±

-0.76

ensis

-0.76

aires

-0.72

 Goodman

-0.70

omical

-0.70

EGA

-0.70

ivals

-0.69

ĸļ

-0.69

 disadvant

-0.69

POSITIVE LOGITS

 instrument

0.72

phrine

0.71

à©

0.69

mitted

0.69

 typed

0.68

lishing

0.66

manship

0.65

ptr

0.64

gress

0.64

utenant

0.64

Activations Density 0.038%

commands or functions related to reading and writing data in a computer program

terms related to writing and file operations

No Comments

No Known Activations