INDEX

Explanations

references to significant events or public figures in political discourse

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Genie

-0.61

 broom

-0.59

 successive

-0.56

chairs

-0.56

 fundamentals

-0.55

paio

-0.55

 sterile

-0.53

phia

-0.53

 secretaries

-0.53

 deviations

-0.52

POSITIVE LOGITS

th

0.96

0.87

0.79

eteenth

0.77

Reply

0.77

0.75

ember

0.74

0.73

Activations Density 0.024%

references to significant events or public figures in political discourse

No Comments

No Known Activations