INDEX

Explanations

phrases that involve guidance or direction related to plans or actions

oai_token-act-pair · gpt-4o-mini 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

©¶æ¥µ

-0.81

cffff

-0.80

Â²

-0.80

phia

-0.76

eps

-0.74

``

-0.73

Ò

-0.73

soever

-0.73

aunder

-0.73

tap

-0.72

POSITIVE LOGITS

 specifics

0.90

why

0.87

 those

0.77

 myself

0.75

 whether

0.75

 fairness

0.73

how

0.72

 questions

0.72

 preventing

0.69

gotten

0.69

Activations Density 0.054%

phrases that involve guidance or direction related to plans or actions

No Comments

No Known Activations