INDEX

Explanations

phrases indicating negative experiences or challenges

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Rica

-0.74

 Borders

-0.69

 Lanka

-0.69

 Lovecraft

-0.65

 Clyde

-0.64

 Richards

-0.63

 Gillespie

-0.63

 McGr

-0.63

 Reyes

-0.61

Ell

-0.61

POSITIVE LOGITS

thirds

1.53

legged

1.36

year

1.34

dimensional

1.34

sided

1.31

digit

1.27

month

1.26

fif

1.25

footed

1.24

minute

1.21

Activations Density 0.039%

phrases indicating negative experiences or challenges

No Comments

No Known Activations