INDEX

Explanations

names, specifically surnames ending with "roney" or "haney"

oai_token-act-pair · gpt-3.5-turbo

names of individuals and their roles or associations

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

wcs

-0.71

oulos

-0.65

 flick

-0.62

nesday

-0.61

heric

-0.61

 Perspective

-0.61

bley

-0.60

akeru

-0.60

 puzz

-0.59

itiveness

-0.59

POSITIVE LOGITS

sbm

0.75

abet

0.73

ItemImage

0.72

äºĶ

0.71

lah

0.71

ĳå£«

0.70

gha

0.67

iple

0.67

nih

0.65

Quantity

0.64

Activations Density 0.208%

names, specifically surnames ending with "roney" or "haney"

names of individuals and their roles or associations

No Comments

No Known Activations