INDEX

Explanations

words related to feelings of heaviness or burden

oai_token-act-pair · gpt-3.5-turbo

terms related to the concepts of boundlessness or unhappiness

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

anwhile

-0.86

 Nanto

-0.81

 Carbuncle

-0.81

cair

-0.78

tsky

-0.76

enegger

-0.73

å§«

-0.73

fman

-0.72

uyomi

-0.72

 Mata

-0.69

POSITIVE LOGITS

rep

0.97

ishable

0.90

assuming

0.89

rave

0.78

unp

0.78

anging

0.77

ashed

0.76

itt

0.76

irable

0.75

orter

0.75

Activations Density 0.016%

words related to feelings of heaviness or burden

terms related to the concepts of boundlessness or unhappiness

No Comments

No Known Activations