INDEX

Explanations

actions or processes that are ongoing, particularly with a sense of continuity or simultaneous tasks

oai_token-act-pair · gpt-3.5-turbo

phrases indicating ongoing actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Christy

-0.84

×Ļ

-0.72

×Ļ×

-0.68

 Regist

-0.66

 GOODMAN

-0.66

 ASAP

-0.66

×

-0.64

 Recommend

-0.64

 grit

-0.63

×ª

-0.63

POSITIVE LOGITS

ebus

0.77

umenthal

0.76

unin

0.76

inki

0.76

ensibly

0.75

obi

0.71

nown

0.71

maxwell

0.71

construct

0.71

iating

0.70

Activations Density 0.173%

actions or processes that are ongoing, particularly with a sense of continuity or simultaneous tasks

phrases indicating ongoing actions or states

No Comments

No Known Activations