INDEX

Explanations

discussions or descriptions of statements made by individuals

oai_token-act-pair · gpt-3.5-turbo

statements or claims followed by explanations or elaborations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

soDeliveryDate

-0.75

Built

-0.74

wcsstore

-0.74

Offline

-0.68

Made

-0.67

iami

-0.66

mite

-0.65

ovych

-0.64

Born

-0.63

 tainted

-0.62

POSITIVE LOGITS

:]

1.15

 summar

1.13

 recount

1.13

 remark

1.09

 sarcast

1.08

 reminis

1.07

 explaining

1.07

 remarks

1.07

 elabor

1.06

 mentioning

1.06

Activations Density 0.339%

discussions or descriptions of statements made by individuals

statements or claims followed by explanations or elaborations

No Comments

No Known Activations