INDEX

Explanations

political statements and discussions

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

nig

-0.82

 ILCS

-0.71

 selves

-0.70

/-

-0.63

Exper

-0.61

Tank

-0.61

Eva

-0.59

 hinge

-0.58

 scratch

-0.58

MJ

-0.57

POSITIVE LOGITS

enegger

0.90

 himself

0.86

 condem

0.76

 congratulated

0.75

 scathing

0.73

 stern

0.73

 applaud

0.71

ursday

0.71

 resigned

0.71

terday

0.70

Activations Density 2.285%

political statements and discussions

No Comments

No Known Activations