INDEX

Explanations

references to original versions or originals

oai_token-act-pair · gpt-3.5-turbo

instances of the word "original"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orney

-0.74

robe

-0.72

risome

-0.70

rogens

-0.69

opping

-0.69

walk

-0.69

abad

-0.68

=-=-=-=-=-=-=-=-

-0.68

rom

-0.65

ammy

-0.64

POSITIVE LOGITS

ITY

0.93

 incarnation

0.89

ity

0.88

 batch

0.79

Filename

0.77

 impetus

0.77

ãĥīãĥ©ãĤ´ãĥ³

0.76

isations

0.75

 trilogy

0.75

istar

0.71

Activations Density 0.016%

references to original versions or originals

instances of the word "original"

No Comments

No Known Activations