INDEX

Explanations

terms related to mechanical components, specifically gears

oai_token-act-pair · gpt-3.5-turbo

references to gear or equipment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

CTR

-0.92

Mub

-0.72

PsyNetMessage

-0.69

 Sheen

-0.67

Bie

-0.67

 Quincy

-0.66

Osw

-0.66

Fuk

-0.65

aukee

-0.64

Klu

-0.64

POSITIVE LOGITS

box

1.22

boxes

1.13

bag

0.96

 gear

0.92

bags

0.84

shift

0.81

gear

0.79

wagon

0.79

 worn

0.75

ifted

0.74

Activations Density 0.029%

terms related to mechanical components, specifically gears

references to gear or equipment

No Comments

No Known Activations