INDEX

Explanations

keywords related to philosophical concepts or discussions

oai_token-act-pair · gpt-3.5-turbo

terminology related to philosophical concepts and discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

esty

-0.80

rake

-0.72

redd

-0.72

ardless

-0.70

tower

-0.68

ording

-0.67

imgur

-0.67

lain

-0.66

sg

-0.66

ords

-0.66

POSITIVE LOGITS

 curiosity

0.94

ophical

0.89

 underpin

0.86

 philosopher

0.86

 philosophers

0.86

 philosophical

0.83

 prec

0.76

 philosoph

0.74

 theoret

0.74

 dile

0.73

Activations Density 0.015%

keywords related to philosophical concepts or discussions

terminology related to philosophical concepts and discussions

No Comments

No Known Activations