INDEX

Explanations

phrases related to reactions and responses to actions or statements

oai_token-act-pair · gpt-3.5-turbo

instances of the word "met" in relation to various responses or reactions

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

 slic

-0.67

 Recon

-0.66

 commentary

-0.63

 floats

-0.62

iod

-0.61

 tentacles

-0.60

 annex

-0.58

 Courier

-0.57

EStreamFrame

-0.56

 Tablet

-0.53

POSITIVE LOGITS

amorph

1.58

ropolis

1.29

tle

1.20

ered

1.15

agame

1.13

onym

1.11

rical

1.07

atars

1.04

rose

1.01

rior

0.98

Activations Density 0.025%

phrases related to reactions and responses to actions or statements

instances of the word "met" in relation to various responses or reactions

No Comments

No Known Activations