INDEX

Explanations

references to continuous or ongoing actions or events

oai_token-act-pair · gpt-3.5-turbo

phrases indicating ongoing processes or trends

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ahime

-0.81

quer

-0.79

LCS

-0.76

lua

-0.73

fit

-0.73

arta

-0.73

md

-0.73

ooters

-0.71

ocene

-0.71

tag

-0.70

POSITIVE LOGITS

 insistence

1.09

 scrutiny

1.05

 reliance

1.03

 absence

1.00

 existence

1.00

 exposure

1.00

 presence

0.98

 vigilance

0.98

 harassment

0.97

 inability

0.96

Activations Density 0.105%

references to continuous or ongoing actions or events

phrases indicating ongoing processes or trends

No Comments

No Known Activations