INDEX

Explanations

instances of the word "mistake"

oai_token-act-pair · gpt-3.5-turbo

references to mistakes or errors

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ighth

-0.80

electric

-0.77

rollers

-0.76

borg

-0.73

well

-0.71

markets

-0.69

zona

-0.69

vez

-0.67

tsky

-0.66

bians

-0.66

POSITIVE LOGITS

 mistakes

0.86

 mistake

0.81

%%%%

0.73

pelled

0.71

 unfocusedRange

0.68

 ACTIONS

0.68

steps

0.65

 mistaken

0.63

 errors

0.63

 Malf

0.63

Activations Density 0.028%

instances of the word "mistake"

references to mistakes or errors

No Comments

No Known Activations