INDEX

Explanations

proper nouns related to organizations

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Inter" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 deduction

-0.70

 scratch

-0.70

 deaf

-0.65

 deductions

-0.65

[+

-0.63

 jobs

-0.63

*/(

-0.62

 pseud

-0.62

ongs

-0.60

OPLE

-0.60

POSITIVE LOGITS

continental

1.28

lude

1.22

ventions

1.16

governmental

1.11

pol

1.11

stitial

1.09

disciplinary

1.07

agency

1.07

Contin

1.06

mediate

1.05

Activations Density 0.013%

proper nouns related to organizations

mentions of the term "Inter" in various contexts

No Comments

No Known Activations