INDEX

Explanations

statements or descriptions

oai_token-act-pair · gpt-3.5-turbo

various types of colons or punctuation that introduce lists or explanations

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

ento

-0.75

 accustomed

-0.74

velt

-0.69

atible

-0.67

aign

-0.67

izons

-0.66

uly

-0.64

ceivable

-0.64

amo

-0.64

 dotted

-0.63

POSITIVE LOGITS

 namely

1.59

Its

0.79

 Firstly

0.70

 Something

0.69

 Marijuana

0.68

 Someone

0.68

 Their

0.67

 Calling

0.67

viz

0.66

 Exploration

0.66

Activations Density 0.209%

statements or descriptions

various types of colons or punctuation that introduce lists or explanations

No Comments

No Known Activations