INDEX

Explanations

words related to specific names, particularly "Mayer"

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ivity

-0.74

rend

-0.74

verted

-0.65

away

-0.62

acters

-0.61

ifts

-0.61

claimed

-0.61

ordinate

-0.60

 microwave

-0.60

 MacArthur

-0.60

POSITIVE LOGITS

hattan

0.85

useum

0.85

ONEY

0.83

emonic

0.77

ixture

0.76

arijuana

0.75

 Mayhem

0.75

ORPG

0.74

HAEL

0.73

achine

0.73

Activations Density 0.190%

words related to specific names, particularly "Mayer"

references to specific individuals and organizations

No Comments

No Known Activations