INDEX

Explanations

references to strangers and their interactions 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

rates

-0.87

umen

-0.78

alist

-0.77

iox

-0.75

arist

-0.74

prus

-0.73

rity

-0.72

rix

-0.71

vez

-0.70

rate

-0.70

POSITIVE LOGITS

liness

0.86

 whom

0.86

 flung

0.84

 grop

0.82

hood

0.82

who

0.82

 alike

0.78

 strangers

0.76

 stranger

0.74

ishly

0.73

Activations Density 0.008%

references to strangers and their interactions in various contexts

No Comments

No Known Activations