INDEX

Explanations

specific mentions of the word "line" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to specific "Line" identifiers or segments in a structured content format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

CVE

-0.83

sylvania

-0.72

âĺħâĺħ

-0.70

ilton

-0.66

ILD

-0.64

cia

-0.63

 salts

-0.63

CLASSIFIED

-0.63

STEM

-0.63

soever

-0.62

POSITIVE LOGITS

backer

1.29

ups

1.20

aments

1.14

breaks

1.04

ages

1.03

breaking

0.93

up

0.92

break

0.90

breakers

0.85

draw

0.78

Activations Density 0.059%

specific mentions of the word "line" in various contexts

references to specific "Line" identifiers or segments in a structured content format

No Comments

No Known Activations