INDEX

Explanations

supportive language

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

apeake

-0.72

 pores

-0.65

tein

-0.62

 Hebdo

-0.60

 sweat

-0.60

sa

-0.59

ãĥ£

-0.59

cffffcc

-0.58

 dare

-0.58

iren

-0.57

POSITIVE LOGITS

Support

0.81

ament

0.77

arity

0.77

heses

0.76

itism

0.74

 Vector

0.73

 Supports

0.72

pport

0.72

bands

0.70

ably

0.69

Activations Density 0.637%

supportive language

No Comments

No Known Activations