INDEX

Explanations

words associated with standing or stationary concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hower

-0.78

merce

-0.71

 friendly

-0.68

EStream

-0.67

ļéĨĴ

-0.65

iferation

-0.64

 Republic

-0.64

MpServer

-0.64

hound

-0.61

ptive

-0.60

POSITIVE LOGITS

uffed

1.22

alker

1.14

itched

1.13

inky

1.12

inging

1.12

amped

1.11

roller

1.11

onew

1.10

umbles

1.07

alks

1.06

Activations Density 0.016%

words associated with standing or stationary concepts

No Comments

No Known Activations