INDEX

Explanations

action verbs and phrases related to decision-making

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

teness

-0.70

txt

-0.69

naires

-0.64

 Boat

-0.64

 Hicks

-0.63

OTOS

-0.61

 Porter

-0.60

ORPG

-0.59

 Davidson

-0.59

Cra

-0.58

POSITIVE LOGITS

 interact

0.96

 differs

0.84

 geographically

0.84

 communicate

0.84

 interpreting

0.82

 interacts

0.81

 interpret

0.81

 behave

0.81

 differ

0.79

 proceed

0.79

Activations Density 2.293%

action verbs and phrases related to decision-making

No Comments

No Known Activations