INDEX

Explanations

mentions of in-depth analysis or descriptions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "in" related to various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

theless

-0.67

 Wizards

-0.63

 Sorceress

-0.62

ghai

-0.60

 alternatively

-0.59

HAEL

-0.59

 Witches

-0.59

OMG

-0.59

 Mistress

-0.59

 DRAG

-0.59

POSITIVE LOGITS

ordinate

1.41

organic

1.41

animate

1.40

activity

1.35

breeding

1.35

patient

1.34

effic

1.33

 vitro

1.33

roads

1.32

humane

1.31

Activations Density 0.088%

mentions of in-depth analysis or descriptions

instances of the word "in" related to various contexts

No Comments

No Known Activations