INDEX

Explanations

phrases related to instructions or requirements

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

 Weston

-0.67

 Reef

-0.64

 Allied

-0.60

 Parkinson

-0.58

));

-0.54

pup

-0.53

 Manny

-0.53

 Constantin

-0.52

 reprinted

-0.52

 Vita

-0.51

POSITIVE LOGITS

theless

0.98

vernment

0.94

usterity

0.92

É

0.92

estine

0.90

mosp

0.89

[/

0.87

lihood

0.83

anmar

0.82

\)

0.82

Activations Density 1.989%

phrases related to instructions or requirements

No Comments

No Known Activations