INDEX

Explanations

terms related to evaluation or assessment processes, particularly in contexts of performance or background checks

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

hold

-0.66

aceous

-0.60

çİĭ

-0.60

Ire

-0.59

icka

-0.59

ines

-0.58

 Comfort

-0.57

 Endurance

-0.57

 Cruel

-0.57

 Crusher

-0.56

POSITIVE LOGITS

 prospect

0.90

committee

0.80

 hiring

0.78

arthed

0.77

 ideas

0.77

mitted

0.77

 hypotheses

0.76

Draft

0.76

 sugg

0.76

 prospects

0.76

Activations Density 0.035%

terms related to evaluation or assessment processes, particularly in contexts of performance or background checks

No Comments

No Known Activations