INDEX

Explanations

the name "Jeffrey"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Jeffrey"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

overs

-0.80

ctrl

-0.76

accompan

-0.76

dayName

-0.76

otin

-0.73

bleacher

-0.73

edition

-0.72

conserv

-0.71

isphere

-0.71

escape

-0.71

POSITIVE LOGITS

rey

1.05

 Epstein

0.97

 Jeffrey

0.95

reys

0.94

 Sachs

0.92

 Potter

0.86

erson

0.85

Dah

0.85

 Wright

0.84

 Goldberg

0.80

Activations Density 0.011%

the name "Jeffrey"

occurrences of the name "Jeffrey"

No Comments

No Known Activations