INDEX

Explanations

sentences summarizing conclusions or key points

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥĺ

-0.84

roups

-0.74

ipel

-0.72

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.70

DOM

-0.68

TIT

-0.68

chlor

-0.66

legged

-0.66

leted

-0.64

itialized

-0.63

POSITIVE LOGITS

 takeaway

0.98

 boils

0.86

 message

0.76

 verdict

0.75

nings

0.73

 perspective

0.72

 approach

0.69

 nutshell

0.69

 lesson

0.68

Activations Density 0.056%

sentences summarizing conclusions or key points

No Comments

No Known Activations