INDEX

Explanations

references to specific phrases like "Paradigm Shift" and "paradigm"

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nery

-0.73

hire

-0.73

llah

-0.70

ertodd

-0.69

packing

-0.66

alties

-0.66

cffff

-0.65

urion

-0.63

idan

-0.63

POSITIVE LOGITS

igmatic

0.92

 shift

0.91

 paradigm

0.91

 Shift

0.88

igm

0.81

 shifts

0.79

geist

0.76

 parad

0.73

atically

0.72

 Parad

0.70

Activations Density 0.033%

references to specific phrases like "Paradigm Shift" and "paradigm"

No Comments

No Known Activations