INDEX

Explanations

technical terms related to software development, security, and testing

oai_token-act-pair · gpt-3.5-turbo

references to health-related topics and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

lyak

-0.77

":"/

-0.76

tsky

-0.74

jected

-0.69

ppo

-0.68

iev

-0.66

gression

-0.66

ction

-0.65

obin

-0.65

rament

-0.64

POSITIVE LOGITS

etc

1.82

etc

1.55

ect

0.90

 respectively

0.84

 assorted

0.82

 vitamins

0.76

 adultery

0.76

Downloadha

0.75

whatever

0.71

 nutritional

0.70

Activations Density 0.204%

technical terms related to software development, security, and testing

references to health-related topics and conditions

No Comments

No Known Activations