INDEX

Explanations

concepts related to recognition and identification of individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

ruary

-0.80

emetery

-0.79

ortium

-0.77

arij

-0.77

grim

-0.76

isSpecialOrderable

-0.76

VD

-0.76

backer

-0.75

ammy

-0.72

FactoryReloaded

-0.72

POSITIVE LOGITS

 stimuli

1.20

 cues

1.11

 signals

1.05

 vibrations

0.92

 inputs

0.92

 incoming

0.88

 oxygen

0.88

 photons

0.87

 objects

0.87

 instinctively

0.83

Activations Density 0.168%

concepts related to recognition and identification of individuals or entities

No Comments

No Known Activations