INDEX

Explanations

words related to size, dimensions, and measurements

oai_token-act-pair · gpt-3.5-turbo

conjunctions and nouns related to size, shape, and health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ievers

-0.77

 Pigs

-0.72

lear

-0.71

sts

-0.71

paren

-0.69

gdala

-0.68

 Kirin

-0.68

arettes

-0.67

quished

-0.67

KEN

-0.66

POSITIVE LOGITS

 breadth

1.11

 stature

1.08

 likeness

1.08

 severity

1.04

 cumbers

1.01

 magnitude

1.01

 dimensions

1.00

 thickness

1.00

 elevation

0.99

 width

0.97

Activations Density 0.279%

words related to size, dimensions, and measurements

conjunctions and nouns related to size, shape, and health

No Comments

No Known Activations