INDEX

Explanations

short words or phrases related to causality or consequence

oai_token-act-pair · gpt-3.5-turbo

phrases indicating transitions or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

utters

-0.76

stall

-0.74

load

-0.70

illed

-0.69

oute

-0.68

redit

-0.67

ins

-0.67

onite

-0.66

ldon

-0.66

aren

-0.63

POSITIVE LOGITS

 guise

0.92

 context

0.79

 manner

0.79

 fashion

0.77

 respects

0.76

 vicinity

0.74

 haste

0.74

 meantime

0.73

çī

0.70

Ø³

0.70

Activations Density 0.144%

short words or phrases related to causality or consequence

phrases indicating transitions or conclusions

No Comments

No Known Activations