INDEX

Explanations

names or topics related to robotics

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

WAYS

-0.83

LOAD

-0.76

 halls

-0.70

uated

-0.69

cence

-0.68

SEE

-0.65

RED

-0.62

tin

-0.61

uates

-0.60

Phase

-0.59

POSITIVE LOGITS

esp

0.95

otics

0.94

ician

0.94

bery

0.90

ageddon

0.90

inson

0.88

otic

0.84

bie

0.83

arest

0.82

ust

0.82

Activations Density 1.072%

names or topics related to robotics

No Comments

No Known Activations