INDEX

Explanations

instances of the word "disclosure" or its related variations

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_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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ieval

-0.82

creation

-0.79

vic

-0.79

stad

-0.69

inal

-0.68

clock

-0.68

Äį

-0.68

jong

-0.68

create

-0.66

twitch

-0.65

POSITIVE LOGITS

 disclosure

0.95

 disclosures

0.94

 Disclosure

0.88

 loopholes

0.85

 disclosing

0.85

 discl

0.83

 disclose

0.81

saf

0.75

 disclosed

0.74

 filings

0.74

Activations Density 0.024%

instances of the word "disclosure" or its related variations

No Comments

No Known Activations