INDEX

Explanations

verbs related to perception and observation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "see" and its variations, indicating observation or awareness

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥĦ

-0.71

TO

-0.71

TA

-0.68

ovie

-0.67

pex

-0.64

ranged

-0.64

oshenko

-0.63

ogo

-0.63

ongyang

-0.63

ilo

-0.63

POSITIVE LOGITS

 ourselves

1.00

 glimps

0.92

 hints

0.85

 signs

0.77

 examples

0.75

 plenty

0.72

 ample

0.71

 indications

0.71

 lots

0.69

 similarities

0.67

Activations Density 0.166%

verbs related to perception and observation

instances of the word "see" and its variations, indicating observation or awareness

No Comments

No Known Activations