INDEX

Explanations

verbs related to descent or decline

oai_token-act-pair · gpt-3.5-turbo

instances of the word "descend" 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

acea

-0.78

stuff

-0.70

keeping

-0.65

OH

-0.61

 Foley

-0.60

ako

-0.59

te

-0.59

sel

-0.59

bara

-0.58

iso

-0.58

POSITIVE LOGITS

 descended

1.05

 descend

1.01

 descent

0.83

ENTS

0.82

 descending

0.78

graded

0.75

ents

0.72

 ancest

0.72

 Seym

0.71

 paths

0.70

Activations Density 0.018%

verbs related to descent or decline

instances of the word "descend" and its variations

No Comments

No Known Activations