INDEX

Explanations

stories or passages related to specific events or interactions in a narrative

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

 affili

-0.94

 extinct

-0.89

 obsolete

-0.74

adian

-0.73

 dracon

-0.72

 microbiome

-0.72

 transact

-0.72

 biological

-0.70

 regenerate

-0.69

 broadly

-0.69

POSITIVE LOGITS

 Afterwards

1.74

 Then

1.72

 Eventually

1.65

 Later

1.56

 Suddenly

1.54

 Luckily

1.50

 Immediately

1.44

 Soon

1.44

 Shortly

1.42

 Upon

1.40

Activations Density 1.539%

stories or passages related to specific events or interactions in a narrative

No Comments

No Known Activations