INDEX

Explanations

references to locations and distances in a narrative

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

Versions

-0.59

 accordingly

-0.56

 handshake

-0.51

 subscript

-0.51

Statement

-0.51

CEO

-0.50

 contingency

-0.48

 negotiator

-0.48

 behav

-0.48

TPP

-0.48

POSITIVE LOGITS

 northwest

0.98

 southwestern

0.95

 northeastern

0.95

 southwest

0.94

 northwestern

0.93

 northeast

0.92

 southeastern

0.92

 southeast

0.91

 eastern

0.90

 northern

0.88

Activations Density 0.401%

references to locations and distances in a narrative

No Comments

No Known Activations