INDEX

Explanations

the word "logical" with a high activation value

oai_token-act-pair · gpt-3.5-turbo

terms related to logical reasoning and argumentation

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

rained

-0.84

raints

-0.74

rums

-0.69

rats

-0.67

ored

-0.67

raint

-0.67

aroo

-0.66

icky

-0.66

acus

-0.65

emo

-0.65

POSITIVE LOGITS

TAIN

0.87

 succession

0.86

 chronological

0.76

lihood

0.75

 leaps

0.75

 posit

0.70

 continuation

0.69

andum

0.69

 extension

0.69

 inference

0.69

Activations Density 0.119%

the word "logical" with a high activation value

terms related to logical reasoning and argumentation

No Comments

No Known Activations