INDEX

Explanations

the name "Alec" with varying degrees of intensity

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Alec" in various contexts

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

ItemThumbnailImage

-0.72

liga

-0.68

-0.66

chool

-0.65

PUR

-0.64

views

-0.64

âĸ¬

-0.64

ularity

-0.63

å£«

-0.63

GN

-0.62

POSITIVE LOGITS

 Alec

1.29

 Baldwin

0.98

odox

0.79

 Corker

0.79

sson

0.78

 Stephens

0.77

akia

0.77

berra

0.76

rities

0.76

throp

0.75

Activations Density 0.017%

the name "Alec" with varying degrees of intensity

mentions of the name "Alec" in various contexts

No Comments

No Known Activations