INDEX

Explanations

mentions of unfortunate events or circumstances

oai_token-act-pair · gpt-3.5-turbo

expressions of misfortune or regret

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ynthesis

-0.87

venants

-0.79

alach

-0.78

aver

-0.75

runners

-0.74

cellent

-0.73

runner

-0.73

paio

-0.72

tein

-0.72

orney

-0.72

POSITIVE LOGITS

 circumstance

0.84

 unfortunate

0.83

 adolesc

0.82

 consequence

0.77

 circumstances

0.76

 souls

0.72

 accidents

0.70

 fools

0.70

 fate

0.70

 Tales

0.69

Activations Density 0.019%

mentions of unfortunate events or circumstances

expressions of misfortune or regret

No Comments

No Known Activations