INDEX

Explanations

instances of the word "corruption" and related concepts

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

leigh

-0.77

imus

-0.74

nee

-0.72

 Advent

-0.69

lee

-0.67

AY

-0.66

eele

-0.65

thur

-0.64

nesium

-0.64

tz

-0.64

POSITIVE LOGITS

 scandals

1.09

 perpetrated

0.98

 corruption

0.96

 graft

0.87

 allegations

0.86

ulent

0.85

 endemic

0.85

 dealings

0.84

 scandal

0.83

 corrupt

0.82

Activations Density 0.021%

instances of the word "corruption" and related concepts

No Comments

No Known Activations