INDEX

Explanations

instances of the word "groping" and similar variations relating to unwanted physical contact

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

 tune

-0.88

 Tune

-0.70

REE

-0.69

senal

-0.69

SO

-0.68

Effective

-0.68

VID

-0.68

VIS

-0.67

DIT

-0.66

 ministry

-0.65

POSITIVE LOGITS

 grop

1.12

ingly

0.89

ing

0.89

atted

0.89

ured

0.87

estation

0.86

ographs

0.85

eties

0.85

raped

0.85

ating

0.84

Activations Density 0.006%

instances of the word "groping" and similar variations relating to unwanted physical contact

No Comments

No Known Activations