INDEX

Explanations

quantities with units

oai_token-act-pair · gpt-3.5-turbo

quantifiable measurements or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

few

-0.95

months

-0.81

-0.76

 Cosponsors

-0.75

humans

-0.75

artist

-0.75

soDeliveryDate

-0.74

entimes

-0.74

ulhu

-0.73

heses

-0.72

POSITIVE LOGITS

 cumulative

0.84

 extra

0.81

 material

0.79

 additional

0.78

 equipment

0.77

 usable

0.76

 coastline

0.75

 concentrated

0.75

 aggregate

0.75

 unprotected

0.74

Activations Density 0.082%

quantities with units

quantifiable measurements or statistics

No Comments

No Known Activations