INDEX

Explanations

proper names related to the name "Andre"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Andre."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

inct

-0.91

stakes

-0.76

dfx

-0.75

lishing

-0.74

ulhu

-0.73

ulum

-0.70

manship

-0.70

yrinth

-0.69

lished

-0.68

egg

-0.67

POSITIVE LOGITS

tti

1.07

 Andre

0.92

byss

0.88

essen

0.82

 Paste

0.76

cats

0.76

 Gord

0.74

 Damon

0.73

 Anton

0.72

 Peyton

0.71

Activations Density 0.006%

proper names related to the name "Andre"

occurrences of the name "Andre."

No Comments

No Known Activations