INDEX

Explanations

mentions of specific dates, events, or entities in the form of articles or stories

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

 allowance

-0.77

unts

-0.77

 extinct

-0.76

 idle

-0.75

 consistency

-0.74

hug

-0.74

 elbow

-0.74

 ditch

-0.73

 attrition

-0.70

 forestry

-0.69

POSITIVE LOGITS

 Previously

1.41

 Initially

1.39

 Though

1.35

 Along

1.35

Its

1.35

 Located

1.34

 Their

1.34

 Unfortunately

1.34

 Specifically

1.33

 Afterwards

1.33

Activations Density 2.912%

mentions of specific dates, events, or entities in the form of articles or stories

No Comments

No Known Activations