INDEX

Explanations

mentions of a specific phrase or term "Bon" with some variations in formatting

oai_token-act-pair · gpt-3.5-turbo

repeated instances of the word "Bon" 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

INAL

-0.67

ODE

-0.65

REAM

-0.56

¥

-0.55

 Ethics

-0.55

DonaldTrump

-0.54

 proofs

-0.53

UX

-0.53

ELD

-0.52

 Redux

-0.52

POSITIVE LOGITS

anza

1.28

kers

1.13

obos

1.09

obo

1.07

eless

1.03

zai

0.99

nie

0.98

bon

0.98

anz

0.98

hom

0.96

Activations Density 0.029%

mentions of a specific phrase or term "Bon" with some variations in formatting

repeated instances of the word "Bon" in various contexts

No Comments

No Known Activations