INDEX

Explanations

mentions of terms related to healthcare policies and political analysis

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

 Blazers

-0.76

 Slate

-0.72

DIR

-0.71

aldi

-0.70

ãĥ¼ãĤ¯

-0.68

 Ellison

-0.66

 Hawks

-0.66

rimp

-0.65

 Twins

-0.64

 Rochester

-0.63

POSITIVE LOGITS

fulness

0.99

abuse

0.99

 substances

0.96

 abusers

0.94

amphetamine

0.91

 Abuse

0.91

 abuse

0.87

 abuser

0.87

iveness

0.86

uality

0.85

Activations Density 0.024%

mentions of terms related to healthcare policies and political analysis

No Comments

No Known Activations