INDEX

Explanations

references to tax-related terms

oai_token-act-pair · gpt-3.5-turbo

references to tax-related topics and issues

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

Ò

-0.83

 Jenner

-0.76

 Hundred

-0.76

 Watts

-0.70

 Despair

-0.70

Osw

-0.69

theless

-0.69

 Sisters

-0.69

Jem

-0.68

 Ange

-0.68

POSITIVE LOGITS

payer

1.22

onomic

1.14

onomy

1.14

onom

1.12

 collectors

1.06

payers

0.95

 collector

0.92

 havens

0.90

paying

0.89

 levied

0.88

Activations Density 0.030%

references to tax-related terms

references to tax-related topics and issues

No Comments

No Known Activations