INDEX

Explanations

terms related to policy, political positions, and policy implications

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

 Stain

-0.80

ITNESS

-0.77

upon

-0.70

batch

-0.66

amate

-0.66

 Templ

-0.66

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.65

ymes

-0.65

apy

-0.65

DAY

-0.65

POSITIVE LOGITS

 makers

0.97

making

0.95

 prescriptions

0.93

 agenda

0.90

 advisor

0.85

 choices

0.85

 adviser

0.84

 policies

0.83

 escalation

0.82

 formulation

0.82

Activations Density 0.488%

terms related to policy, political positions, and policy implications

No Comments

No Known Activations