INDEX

Explanations

mentions of specific numbers or statistics pertaining to certain topics

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

degree

-0.58

ADS

-0.57

amb

-0.56

 denial

-0.55

track

-0.54

ammy

-0.53

theless

-0.53

ãĥ¯ãĥ³

-0.52

 sequel

-0.52

RP

-0.51

POSITIVE LOGITS

othes

1.10

othe

1.02

apy

1.00

bered

0.98

far

0.97

oner

0.91

aps

0.89

oths

0.88

aks

0.80

far

0.79

Activations Density 0.060%

mentions of specific numbers or statistics pertaining to certain topics

No Comments

No Known Activations