INDEX

Explanations

phrases expressing gratitude and appreciation

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

 Cosponsors

-0.74

Fla

-0.67

TN

-0.66

osponsors

-0.66

cue

-0.66

bol

-0.62

Switch

-0.59

wcsstore

-0.59

deck

-0.58

Specifically

-0.58

POSITIVE LOGITS

 stagn

0.81

 starve

0.77

 doomed

0.77

 wouldn

0.75

 collapses

0.74

 meaningless

0.73

 stagnation

0.72

 unman

0.68

 fragile

0.68

 chances

0.67

Activations Density 0.169%

phrases expressing gratitude and appreciation

No Comments

No Known Activations