INDEX

Explanations

mentions of the term "Bayesian"

oai_token-act-pair · gpt-3.5-turbo

references to the Bay Area

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

mble

-0.77

matter

-0.72

iferation

-0.68

qqa

-0.68

cussion

-0.68

etimes

-0.66

ional

-0.65

etsk

-0.64

nesday

-0.64

DonaldTrump

-0.64

POSITIVE LOGITS

onet

1.19

esian

1.18

Bay

0.96

Bay

0.87

 Area

0.81

olla

0.80

keeper

0.78

bay

0.77

front

0.77

onne

0.75

Activations Density 0.009%

mentions of the term "Bayesian"

references to the Bay Area

No Comments

No Known Activations