INDEX

Explanations

personal and political names, particularly focusing on people involved in controversies or conflicts

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

pmwiki

-0.77

PDATE

-0.69

BALL

-0.69

liga

-0.68

 modernization

-0.65

ledged

-0.63

MENTS

-0.61

OWER

-0.59

REP

-0.59

 favour

-0.57

POSITIVE LOGITS

athan

1.29

Doe

1.08

nie

1.04

ston

1.04

 Cena

1.03

 Hancock

0.96

stone

0.92

stown

0.90

 Quincy

0.89

 Lennon

0.89

Activations Density 0.488%

personal and political names, particularly focusing on people involved in controversies or conflicts

No Comments

No Known Activations