INDEX

Explanations

words or phrases indicating a ranking or level of importance, typically related to being the best or most significant in some context

oai_token-act-pair · gpt-3.5-turbo

references to being "number one" or top-ranked in various contexts

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

utic

-0.79

ifi

-0.71

isure

-0.71

ework

-0.71

itz

-0.71

opian

-0.69

thia

-0.69

agons

-0.68

ornings

-0.67

 Lyons

-0.66

POSITIVE LOGITS

 contender

1.13

 priority

0.90

 ranking

0.87

 bidder

0.86

 ranked

0.82

 trending

0.79

glers

0.78

 earners

0.78

 seller

0.78

 spot

0.78

Activations Density 0.026%

words or phrases indicating a ranking or level of importance, typically related to being the best or most significant in some context

references to being "number one" or top-ranked in various contexts

No Comments

No Known Activations