INDEX

Explanations

words related to contribution or causation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "contribute" 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 @ 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

dar

-0.71

çĦ

-0.69

Fal

-0.68

mares

-0.66

 Demons

-0.64

 Lumpur

-0.63

corn

-0.62

MAT

-0.61

phe

-0.61

ft

-0.60

POSITIVE LOGITS

 materially

0.85

itionally

0.84

 contributing

0.83

itives

0.81

interstitial

0.81

 contribut

0.78

imentary

0.78

umed

0.77

 contribute

0.77

iosyncr

0.77

Activations Density 0.017%

words related to contribution or causation

instances of the word "contribute" and its variations

No Comments

No Known Activations