INDEX

Explanations

names of individuals and their involvement in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

ãĤ¡

-0.68

CRE

-0.67

Americ

-0.63

ãĥ¬

-0.62

-0.60

ween

-0.59

 ..."

-0.58

-0.57

SAM

-0.57

-0.56

POSITIVE LOGITS

 reportedly

1.12

 meanwhile

0.95

 denies

0.95

 responded

0.95

 apologized

0.94

 famously

0.94

 allegedly

0.91

 testified

0.91

 sacked

0.90

 vetoed

0.88

Activations Density 0.187%

names of individuals and their involvement in various contexts

No Comments

No Known Activations