INDEX

Explanations

occurrences of the word "asked" and its variants in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ĥ¬

-0.70

Fit

-0.68

herence

-0.66

Est

-0.63

ources

-0.62

 mars

-0.61

 Siber

-0.60

 Confeder

-0.59

rats

-0.59

Inc

-0.57

POSITIVE LOGITS

 questions

1.11

 repeatedly

0.90

 question

0.88

 rhet

0.86

naires

0.86

 asked

0.84

naire

0.82

 probing

0.81

 forgiveness

0.80

 Questions

0.78

Activations Density 0.018%

occurrences of the word "asked" and its variants in various contexts

No Comments

No Known Activations