INDEX

Explanations

negations or contradictions

oai_token-act-pair · gpt-3.5-turbo

negations or phrases that indicate a lack of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 spor

-0.66

 indirectly

-0.65

tein

-0.64

 creations

-0.62

arts

-0.61

Js

-0.58

 rotated

-0.57

 oriented

-0.57

 towed

-0.56

 jointly

-0.56

POSITIVE LOGITS

 unanim

0.93

hin

0.87

enough

0.86

 enough

0.81

xus

0.81

 room

0.80

ibaba

0.79

Enough

0.77

ANY

0.76

 anymore

0.73

Activations Density 0.070%

negations or contradictions

negations or phrases that indicate a lack of something

No Comments

No Known Activations