INDEX

Explanations

terms related to computational concepts and programming languages, particularly focusing on syntax, data structures, and linguistic notation

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

rollers

-0.81

oslav

-0.74

icons

-0.73

wives

-0.73

pill

-0.70

cycles

-0.70

istors

-0.69

 Scores

-0.68

berries

-0.68

boards

-0.68

POSITIVE LOGITS

 latter

1.08

 phenomenon

1.06

 discrepancy

1.00

 reasoning

0.99

 complication

0.99

 assertion

0.93

 arrangement

0.91

 newfound

0.91

 circumstance

0.88

 trend

0.87

Activations Density 1.268%

terms related to computational concepts and programming languages, particularly focusing on syntax, data structures, and linguistic notation

No Comments

No Known Activations