INDEX

Explanations

the concept of drifting or floating away from a point or situation

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

tained

-0.80

terday

-0.72

RON

-0.71

ledged

-0.71

Brave

-0.69

osterone

-0.68

lain

-0.67

ourt

-0.65

eele

-0.65

aurus

-0.64

POSITIVE LOGITS

 drifting

1.01

 drift

0.97

 away

0.97

wood

0.92

 toward

0.88

warm

0.87

 towards

0.85

 Away

0.83

 apart

0.82

 ashore

0.81

Activations Density 0.007%

the concept of drifting or floating away from a point or situation

No Comments

No Known Activations