INDEX

Explanations

terms related to measures of weight or importance

oai_token-act-pair · gpt-3.5-turbo

terms related to measurement scales

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

algia

-0.75

vous

-0.71

riad

-0.70

present

-0.68

 Gore

-0.68

draw

-0.67

nie

-0.66

Ì¶

-0.66

clamation

-0.66

unal

-0.64

POSITIVE LOGITS

 scales

1.23

heet

0.86

 scale

0.82

 Scale

0.77

itized

0.77

acebook

0.75

 shards

0.74

anches

0.73

 instruments

0.72

iless

0.71

Activations Density 0.011%

terms related to measures of weight or importance

terms related to measurement scales

No Comments

No Known Activations