INDEX

Explanations

mentions of the word 'dim'

oai_token-act-pair · gpt-3.5-turbo

references to "dimorphism" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

hips

-0.84

CRIP

-0.79

cially

-0.70

ciating

-0.66

EMENT

-0.63

ALLY

-0.61

omes

-0.60

spr

-0.59

 Rouge

-0.58

Desk

-0.58

POSITIVE LOGITS

inished

1.61

itri

1.38

ethy

1.35

ming

1.28

ples

1.25

orph

1.24

ensions

1.21

pled

1.20

med

1.17

pling

1.13

Activations Density 0.046%

mentions of the word 'dim'

references to "dimorphism" and its variations

No Comments

No Known Activations