INDEX

Explanations

sentences discussing possibilities or potential courses of action

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

 Constant

-0.64

 Fighter

-0.64

feeding

-0.63

ging

-0.63

ocracy

-0.61

raphic

-0.61

 Lifetime

-0.60

performing

-0.60

ciating

-0.60

 Palest

-0.60

POSITIVE LOGITS

onna

1.12

hap

1.11

haps

1.09

bes

1.04

be

1.03

 derive

0.89

 confuse

0.88

owe

0.87

 have

0.81

 misunder

0.81

Activations Density 0.300%

sentences discussing possibilities or potential courses of action

No Comments

No Known Activations