INDEX

Explanations

technical jargon related to pharmaceuticals

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

ing

-1.20

hips

-1.09

edly

-1.07

ed

-1.06

-1.03

ships

-1.02

es

-0.90

ingham

-0.90

sie

-0.89

edin

-0.86

POSITIVE LOGITS

ãĥ¥

0.69

emonic

0.64

 unmarked

0.58

awar

0.58

ãĥĥãĤ¯

0.57

asion

0.57

astically

0.57

bom

0.57

 retard

0.57

 sickness

0.56

Activations Density 2.913%

technical jargon related to pharmaceuticals

No Comments

No Known Activations