INDEX

Explanations

mentions of the name "Harris" in varying contexts

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.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

nces

-0.73

rious

-0.71

zzi

-0.69

eers

-0.64

erous

-0.63

 privilege

-0.60

rous

-0.60

lihood

-0.59

unal

-0.59

uers

-0.58

POSITIVE LOGITS

burg

1.39

burgh

1.01

mann

0.97

abis

0.92

bury

0.89

acre

0.89

alez

0.88

bach

0.88

laughter

0.86

kins

0.85

Activations Density 0.020%

mentions of the name "Harris" in varying contexts

No Comments

No Known Activations