INDEX

Explanations

terms related to news stations and media coverage

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or facilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

STEM

-0.72

ojure

-0.71

ogle

-0.71

":"/

-0.70

aphael

-0.69

erenn

-0.69

vernment

-0.67

 Marketable

-0.64

shaw

-0.63

ulkan

-0.63

POSITIVE LOGITS

 wagon

1.15

 stations

1.12

 station

1.08

wagon

0.82

ery

0.78

 attendant

0.78

piece

0.77

mates

0.75

 retri

0.73

 Station

0.72

Activations Density 0.017%

terms related to news stations and media coverage

references to specific locations or facilities

No Comments

No Known Activations