INDEX

Explanations

phrases related to actions or tasks being done or considered

oai_token-act-pair · gpt-3.5-turbo

verbs that denote actions related to discussion and processing of topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Defenders

-0.66

utra

-0.62

urai

-0.61

 Balance

-0.60

acion

-0.59

communications

-0.59

ultz

-0.58

asio

-0.58

adan

-0.57

riot

-0.57

POSITIVE LOGITS

own

0.93

ĸļ

0.83

oing

0.80

nesday

0.77

gling

0.75

uled

0.74

ired

0.73

 UCHIJ

0.72

escription

0.71

 Alive

0.70

Activations Density 0.264%

phrases related to actions or tasks being done or considered

verbs that denote actions related to discussion and processing of topics

No Comments

No Known Activations