INDEX

Explanations

phrases related to goals or missions

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

 legends

-0.70

ols

-0.70

otal

-0.69

 Solitaire

-0.69

 clips

-0.65

 alloy

-0.64

Edited

-0.64

Poly

-0.61

DOS

-0.61

Du

-0.60

POSITIVE LOGITS

Goal

1.05

 Goal

0.99

 goal

0.96

posts

0.95

goal

0.95

 goals

0.89

lessly

0.86

ims

0.82

 accomplished

0.81

 pursued

0.81

Activations Density 0.830%

phrases related to goals or missions

No Comments

No Known Activations