INDEX

Explanations

verbs that indicate action or activity

oai_token-act-pair · gpt-3.5-turbo

statements about capabilities and functions

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

lie

-0.72

ã

-0.70

oppy

-0.66

ilater

-0.65

igl

-0.63

osaurus

-0.62

 aides

-0.59

jac

-0.58

INT

-0.58

POSITIVE LOGITS

prototype

0.74

£ı

0.73

tesy

0.72

 founder

0.71

ONSORED

0.66

 trending

0.66

 partnered

0.65

 premier

0.65

Plugin

0.63

utenberg

0.61

Activations Density 0.567%

verbs that indicate action or activity

statements about capabilities and functions

No Comments

No Known Activations