INDEX

Explanations

phrases related to strong, intense, or forceful actions or efforts

oai_token-act-pair · gpt-3.5-turbo

terms related to vigorous or concerted actions and efforts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ologies

-0.77

 Tycoon

-0.76

olog

-0.75

 valves

-0.75

iah

-0.71

opathy

-0.68

ramid

-0.65

 Cambodia

-0.64

iland

-0.64

codes

-0.63

POSITIVE LOGITS

 effort

0.94

 bouts

0.80

 endeavour

0.80

 efforts

0.77

ãĥ£

0.77

 vigorous

0.77

 enough

0.72

ly

0.71

 pursuit

0.70

 exert

0.70

Activations Density 0.027%

phrases related to strong, intense, or forceful actions or efforts

terms related to vigorous or concerted actions and efforts

No Comments

No Known Activations