INDEX

Explanations

concepts related to dependency and reliance 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

efer

-0.83

itz

-0.77

ourning

-0.76

tell

-0.75

furt

-0.74

iser

-0.73

mberg

-0.72

tein

-0.71

awar

-0.71

iday

-0.70

POSITIVE LOGITS

encies

1.13

ency

0.97

 injection

0.91

lessly

0.87

 dependency

0.83

 upon

0.76

 strain

0.75

 cooker

0.75

 cripp

0.73

worthiness

0.71

Activations Density 0.011%

concepts related to dependency and reliance in various contexts

No Comments

No Known Activations