INDEX

Explanations

references to the 9/11 terrorist attacks

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

iations

-0.86

iating

-0.83

itably

-0.82

pmwiki

-0.81

iates

-0.76

ividual

-0.75

 Uriel

-0.75

itable

-0.75

iated

-0.74

ively

-0.73

POSITIVE LOGITS

0.99

0.90

ãĤ§

0.86

borough

0.82

0.81

0.78

0.77

ãĥ¼ãĥ³

0.75

masters

0.74

ãĤ©

0.72

Activations Density 2.711%

references to the 9/11 terrorist attacks

No Comments

No Known Activations