INDEX

Explanations

phrases related to justification or reason

oai_token-act-pair · gpt-3.5-turbo

the word "because" in various contexts to indicate reasoning or justification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

mint

-0.75

load

-0.71

tumblr

-0.69

lez

-0.69

Trend

-0.68

conom

-0.68

gren

-0.67

 TABLE

-0.67

 Samson

-0.63

sell

-0.62

POSITIVE LOGITS

nor

0.91

 unsub

0.80

 anymore

0.78

 neither

0.75

 spoilers

0.69

yet

0.69

 censorship

0.69

 lack

0.68

 pesky

0.67

Nor

0.67

Activations Density 0.141%

phrases related to justification or reason

the word "because" in various contexts to indicate reasoning or justification

No Comments

No Known Activations