INDEX

Explanations

proper names related to titles, positions, or individuals

oai_token-act-pair · gpt-3.5-turbo

the name "Brian" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

TOR

-0.75

roxy

-0.75

USE

-0.66

orph

-0.65

artifacts

-0.65

INS

-0.64

UV

-0.64

uph

-0.64

minist

-0.64

allows

-0.62

POSITIVE LOGITS

Moy

0.86

 Cage

0.80

 McCann

0.80

 Blessed

0.79

rics

0.78

nie

0.77

lass

0.76

 Shaw

0.76

 Patrick

0.75

 Fitzpatrick

0.75

Activations Density 0.029%

proper names related to titles, positions, or individuals

the name "Brian" in various contexts

No Comments

No Known Activations