INDEX

Explanations

mentions of academic disciplines, specifically philosophy

oai_token-act-pair · gpt-3.5-turbo

references to philosophy and related academic fields

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

esty

-0.82

ells

-0.80

ookie

-0.76

ilee

-0.75

å¥³

-0.74

cue

-0.71

bring

-0.71

kefeller

-0.70

elight

-0.70

rake

-0.69

POSITIVE LOGITS

ophical

1.32

ophers

0.91

 philosophers

0.90

 philosopher

0.90

ophy

0.83

 philosophy

0.82

ophe

0.82

lectic

0.80

 Philosophy

0.77

opher

0.77

Activations Density 0.023%

mentions of academic disciplines, specifically philosophy

references to philosophy and related academic fields

No Comments

No Known Activations