INDEX

Explanations

references to government officials and their positions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

thood

-0.80

 rave

-0.73

ãĥ¥

-0.71

mable

-0.68

tics

-0.67

 scouts

-0.64

 reproduction

-0.63

 Comput

-0.63

 tattoos

-0.62

books

-0.62

POSITIVE LOGITS

 Democrat

1.17

Republican

1.10

 Republican

1.05

osponsors

1.01

Senate

1.00

Jr

1.00

ospons

0.98

 Democratic

0.96

 Senate

0.95

 bipartisan

0.93

Activations Density 0.070%

references to government officials and their positions

No Comments

No Known Activations