INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

references to specific entities and terms, particularly related to "ND" (New Democracy) and the name "Alice."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Trophy

-0.77

ktop

-0.76

 midrange

-0.75

flex

-0.75

 Finder

-0.74

 Batt

-0.68

icio

-0.68

 champ

-0.66

 Emmanuel

-0.66

 squash

-0.65

POSITIVE LOGITS

ND

2.72

Alice

1.29

 Alice

1.25

 Miranda

1.19

ND

1.13

iba

1.06

 appropriations

1.05

 ALEC

1.03

appropri

1.02

 Appropriations

1.00

Activations Density 0.047%

proper nouns

references to specific entities and terms, particularly related to "ND" (New Democracy) and the name "Alice."

No Comments

No Known Activations