INDEX

Explanations

mentions of news-related terms, particularly related to anchors or news channels

oai_token-act-pair · gpt-3.5-turbo

references to news anchors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ensation

-0.88

wagen

-0.78

STEM

-0.76

govtrack

-0.74

yles

-0.71

ordan

-0.70

esa

-0.69

axies

-0.68

plets

-0.68

ccess

-0.67

POSITIVE LOGITS

 anchor

1.46

 anch

1.33

 anchors

1.24

 anchored

1.13

 Anch

0.87

orage

0.79

 filler

0.77

 enchant

0.76

 tenant

0.75

 reefs

0.74

Activations Density 0.006%

mentions of news-related terms, particularly related to anchors or news channels

references to news anchors

No Comments

No Known Activations