INDEX

Explanations

mentions of a specific word or concept, "Hammer", multiple times at various contexts

oai_token-act-pair · gpt-3.5-turbo

repeated references to specific names and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 polyg

-0.76

yss

-0.74

coy

-0.74

CES

-0.74

LV

-0.72

rang

-0.72

 prepaid

-0.72

hum

-0.71

pas

-0.70

 vide

-0.70

POSITIVE LOGITS

 Hammer

2.75

DW

1.85

 Kaiser

1.41

 Slayer

1.32

 Kirby

1.30

 hammer

1.21

 Penny

1.21

 Slaughter

1.16

 Baird

1.12

 Defender

1.09

Activations Density 0.054%

mentions of a specific word or concept, "Hammer", multiple times at various contexts

repeated references to specific names and organizations

No Comments

No Known Activations