INDEX

Explanations

instances of the word "nod" or related terms

oai_token-act-pair · gpt-3.5-turbo

instances of the word "nod" and its variations 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 tabl

-0.88

inventoryQuantity

-0.74

OTOS

-0.72

 Journals

-0.70

 Hebdo

-0.68

Ļ½

-0.66

Princ

-0.65

ãĥ¯ãĥ³

-0.65

à¦

-0.63

 newsletters

-0.63

POSITIVE LOGITS

nod

1.18

ules

1.10

atory

1.04

endum

1.01

ule

0.99

ularity

0.94

uling

0.93

vironment

0.92

 nods

0.91

emonic

0.87

Activations Density 0.013%

instances of the word "nod" or related terms

instances of the word "nod" and its variations in various contexts

No Comments

No Known Activations