INDEX

Explanations

references to specific individuals named Nick

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Nick."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ãĥ´ãĤ¡

-0.74

ASED

-0.74

 redistributed

-0.73

-0.72

velt

-0.69

WAYS

-0.69

 à¨

-0.69

fare

-0.68

emale

-0.67

ACTED

-0.66

POSITIVE LOGITS

laus

1.31

named

1.11

ety

1.07

names

0.98

olas

0.98

imus

0.93

las

0.92

erson

0.91

ophon

0.90

0.87

Activations Density 0.014%

references to specific individuals named Nick

mentions of the name "Nick."

No Comments

No Known Activations