INDEX

Explanations

specific mentions of the location "NY" with a high degree of activation

oai_token-act-pair · gpt-3.5-turbo

mentions of New York (NY)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ãĥĩãĤ£

-0.83

tackle

-0.81

backer

-0.77

addons

-0.76

pill

-0.76

Topics

-0.75

cies

-0.73

SourceFile

-0.72

Enlarge

-0.71

module

-0.69

POSITIVE LOGITS

RB

0.96

SE

0.91

NY

0.88

NY

0.85

atana

0.77

 Jets

0.74

 Mellon

0.73

 YORK

0.73

 Knicks

0.72

OC

0.72

Activations Density 0.005%

specific mentions of the location "NY" with a high degree of activation

mentions of New York (NY)

No Comments

No Known Activations