INDEX

Explanations

references to senators or the word "Sen."

oai_token-act-pair · gpt-4o-mini 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

 civilisation

-0.72

tru

-0.70

 unmarked

-0.68

 damp

-0.65

 factor

-0.65

 sticky

-0.63

 Siberian

-0.63

 webcam

-0.60

 manual

-0.60

footed

-0.60

POSITIVE LOGITS

iors

1.33

pai

1.05

eca

1.04

escent

1.03

esse

1.01

seless

1.00

iture

0.96

essee

0.93

egal

0.91

uary

0.90

Activations Density 0.011%

references to senators or the word "Sen."

No Comments

No Known Activations