INDEX

Explanations

references to a specific person named Wayne

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Wayne."

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

rador

-1.12

yrinth

-1.03

gently

-0.91

gerald

-0.81

avorite

-0.75

iar

-0.75

TAIN

-0.70

alion

-0.69

*/(

-0.68

inally

-0.67

POSITIVE LOGITS

 Gret

0.96

 Enterprises

0.92

 Rooney

0.91

 Manor

0.83

pton

0.80

 Beach

0.75

 Wayne

0.75

Til

0.75

ufact

0.74

Dug

0.73

Activations Density 0.012%

references to a specific person named Wayne

occurrences of the name "Wayne."

No Comments

No Known Activations