INDEX

Explanations

descriptions of actions or events involving people or organizations

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

onga

-0.66

};

-0.65

}.

-0.61

%.

-0.61

SPONSORED

-0.61

}}

-0.61

Ħ¢

-0.61

VERTISEMENT

-0.57

irable

-0.57

]).

-0.57

POSITIVE LOGITS

 extensively

0.87

 because

0.84

 expecting

0.80

 insofar

0.78

 briefly

0.77

 cautiously

0.75

 intending

0.74

 differently

0.73

 separately

0.70

 yesterday

0.69

Activations Density 4.910%

descriptions of actions or events involving people or organizations

No Comments

No Known Activations