INDEX

Explanations

phrases related to achieving a goal or reaching a certain destination

oai_token-act-pair · gpt-3.5-turbo

phrases related to achieving a goal or reaching a milestone

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

 expressions

-0.65

 motives

-0.63

 passion

-0.63

 affinity

-0.63

bryce

-0.61

 pricing

-0.60

 compr

-0.59

CRE

-0.58

 parallels

-0.58

 spies

-0.58

POSITIVE LOGITS

ozo

0.77

bernatorial

0.76

éĹ

0.72

 stride

0.72

iler

0.71

eline

0.71

osaurs

0.69

sie

0.69

berman

0.69

nder

0.68

Activations Density 0.078%

phrases related to achieving a goal or reaching a certain destination

phrases related to achieving a goal or reaching a milestone

No Comments

No Known Activations