INDEX

Explanations

adjectives related to degree or comparison

oai_token-act-pair · gpt-3.5-turbo

comparative phrases that highlight varying degrees of significance or quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

stead

-0.67

ãĥİ

-0.59

SON

-0.58

ools

-0.58

ãĥīãĥ©ãĤ´ãĥ³

-0.58

Ws

-0.56

POR

-0.56

UCT

-0.54

inders

-0.53

MIN

-0.52

POSITIVE LOGITS

 athlet

0.88

 anymore

0.86

idious

0.84

nor

0.71

as

0.70

amus

0.70

istic

0.70

 defensively

0.69

 than

0.68

itatively

0.68

Activations Density 0.114%

adjectives related to degree or comparison

comparative phrases that highlight varying degrees of significance or quality

No Comments

No Known Activations