INDEX

Explanations

arguments or discussions related to specific beliefs or ideas

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

ECA

-0.69

pin

-0.65

!.

-0.65

%.

-0.62

UF

-0.62

+.

-0.60

si

-0.60

yi

-0.58

kie

-0.57

ãĤ´ãĥ³

-0.57

POSITIVE LOGITS

hesda

0.71

 someone

0.71

 somehow

0.70

ritical

0.70

 bothered

0.67

someone

0.66

 omission

0.65

 hindsight

0.64

 inaction

0.63

 outsiders

0.62

Activations Density 0.130%

arguments or discussions related to specific beliefs or ideas

No Comments

No Known Activations