INDEX

Explanations

words related to criticism or improvement

oai_token-act-pair · gpt-3.5-turbo

terms related to issues, changes, and challenges

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

liv

-0.63

]+

-0.61

td

-0.58

ãĥ´ãĤ¡

-0.56

[|

-0.56

 unequ

-0.56

blast

-0.55

sleep

-0.55

 Submit

-0.55

Interstitial

-0.54

POSITIVE LOGITS

 involves

1.13

 relates

1.09

 revolves

1.04

 arises

0.98

is

0.95

 occurs

0.92

 comes

0.89

 derives

0.87

was

0.87

 concerns

0.84

Activations Density 0.161%

words related to criticism or improvement

terms related to issues, changes, and challenges

No Comments

No Known Activations