INDEX

Explanations

reasoning or explanation related to decisions

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

lez

-0.84

wn

-0.77

nin

-0.71

agin

-0.70

Gas

-0.68

iac

-0.67

hal

-0.66

ax

-0.66

gall

-0.65

yan

-0.64

POSITIVE LOGITS

 they

1.01

 otherwise

0.92

 nobody

0.87

 unlike

0.83

 there

0.82

*/(

0.81

it

0.81

 THEY

0.79

 obviously

0.71

we

0.70

Activations Density 2.933%

reasoning or explanation related to decisions

No Comments

No Known Activations