INDEX

Explanations

phrases related to statements or comments made by individuals

oai_token-act-pair · gpt-3.5-turbo

indicators of significant activities or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

%,

-0.59

estine

-0.58

 corrupt

-0.57

 whereas

-0.56

%;

-0.54

 insofar

-0.51

',

-0.51

paralle

-0.51

','

-0.51

 however

-0.51

POSITIVE LOGITS

 Wednesday

0.71

 Thursday

0.68

 Tuesday

0.66

romptu

0.63

].

0.62

].

0.62

RESULTS

0.62

]."

0.62

 Friday

0.61

.).

0.60

Activations Density 1.129%

phrases related to statements or comments made by individuals

indicators of significant activities or events

No Comments

No Known Activations