INDEX

Explanations

terms related to intersections or decision points

oai_token-act-pair · gpt-3.5-turbo

references to cross-disciplinary themes or intersections 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

nant

-0.72

å§«

-0.72

Peb

-0.71

acious

-0.67

cients

-0.67

ERSON

-0.67

auna

-0.64

idity

-0.64

lain

-0.63

OND

-0.63

POSITIVE LOGITS

roads

1.23

cross

1.04

bow

0.93

bows

0.87

 cross

0.84

bones

0.84

hair

0.84

bench

0.82

cutting

0.81

cut

0.77

Activations Density 0.011%

terms related to intersections or decision points

references to cross-disciplinary themes or intersections in various contexts

No Comments

No Known Activations