INDEX

Explanations

examples of pairings or connections between different entities or concepts

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases related to connections or associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Invalid

-0.75

 partName

-0.72

imet

-0.67

edIn

-0.64

SourceFile

-0.63

Magikarp

-0.62

FML

-0.61

iste

-0.60

TEXTURE

-0.60

phrine

-0.60

POSITIVE LOGITS

etheless

0.96

theless

0.94

 secondly

0.83

 alternatively

0.75

 furthermore

0.74

 thence

0.71

 accordingly

0.62

ther

0.62

ortunately

0.61

 moreover

0.61

Activations Density 0.120%

examples of pairings or connections between different entities or concepts

conjunctions and phrases related to connections or associations

No Comments

No Known Activations