INDEX

Explanations

mentions of the medication "paracetamol" and related terms

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

ħĭ

-0.85

andestine

-0.74

sonian

-0.72

OME

-0.69

ĨĴ

-0.68

sburg

-0.66

 Territories

-0.65

å£«

-0.65

è»

-0.65

=]

-0.65

POSITIVE LOGITS

allel

1.15

anoia

1.06

agraph

1.04

rying

1.00

amount

0.99

vati

0.98

abolic

0.96

ques

0.96

cells

0.96

rots

0.95

Activations Density 0.584%

mentions of the medication "paracetamol" and related terms

No Comments

No Known Activations