INDEX

Explanations

phrases related to limits, constraints, or boundaries

oai_token-act-pair · gpt-3.5-turbo

phrases indicating limitations or constraints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

cellaneous

-0.73

 respectively

-0.64

weeney

-0.64

mosp

-0.62

-0.60

ãĥĩãĤ£

-0.59

HH

-0.58

 abbrevi

-0.57

 awoken

-0.57

 Amen

-0.56

POSITIVE LOGITS

 anymore

1.16

nor

1.09

olithic

0.77

acea

0.72

âĸ

0.72

oshenko

0.72

 necessarily

0.67

gin

0.67

esc

0.65

rites

0.64

Activations Density 0.253%

phrases related to limits, constraints, or boundaries

phrases indicating limitations or constraints

No Comments

No Known Activations