INDEX

Explanations

accusatory language and situations where someone is being accused of something

oai_token-act-pair · gpt-3.5-turbo

instances of accusations against individuals or entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 largeDownload

-0.81

erd

-0.76

 migr

-0.69

phies

-0.65

hedral

-0.65

redo

-0.65

peak

-0.63

pher

-0.62

æĸ¹

-0.62

iasm

-0.62

POSITIVE LOGITS

 accuser

0.80

 alleging

0.77

paio

0.77

 inaction

0.76

icide

0.75

 negligence

0.73

 defendants

0.73

 criminally

0.70

 negligent

0.70

 suppliers

0.69

Activations Density 0.333%

accusatory language and situations where someone is being accused of something

instances of accusations against individuals or entities

No Comments

No Known Activations