INDEX

Explanations

signature elements like symbols or markers separating different sections or articles within a text

oai_token-act-pair · gpt-3.5-turbo

calls to action and engagement prompts

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

Kad

-0.65

 Resolution

-0.64

 assignments

-0.61

 waivers

-0.60

 resid

-0.60

 residency

-0.60

fac

-0.59

 inverse

-0.58

baum

-0.58

 Gardner

-0.58

POSITIVE LOGITS

Actor

0.76

steen

0.74

everal

0.73

CAR

0.72

arnaev

0.72

Pin

0.70

Brow

0.69

 dstg

0.69

Hillary

0.68

ilage

0.68

Activations Density 0.056%

signature elements like symbols or markers separating different sections or articles within a text

calls to action and engagement prompts

No Comments

No Known Activations