INDEX

Explanations

words related to mental activities or states, particularly those expressing complexity or intensity

oai_token-act-pair · gpt-3.5-turbo

phrases relating to mental states or cognitive conditions

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

Ã±o

-0.73

querade

-0.69

ozo

-0.67

orah

-0.61

merce

-0.59

iability

-0.59

rentices

-0.58

iatus

-0.58

 Creed

-0.58

ruary

-0.57

POSITIVE LOGITS

ãĤ´ãĥ³

0.80

bending

0.70

lessness

0.69

 wandering

0.68

consuming

0.66

eering

0.65

oeuv

0.65

apse

0.64

cling

0.64

âĸ¬

0.64

Activations Density 0.076%

words related to mental activities or states, particularly those expressing complexity or intensity

phrases relating to mental states or cognitive conditions

No Comments

No Known Activations