INDEX

Explanations

professor names and associated institutions

oai_token-act-pair · gpt-3.5-turbo

positions or titles of professors associated with academic institutions

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

VALUE

-0.82

worthiness

-0.78

cro

-0.75

Pac

-0.69

VIDEO

-0.68

ptions

-0.68

ptives

-0.66

Russ

-0.66

comfort

-0.66

film

-0.64

POSITIVE LOGITS

 least

0.97

onement

0.88

rial

0.84

abase

0.81

MIT

0.75

DH

0.74

 universities

0.71

 Leaves

0.71

mega

0.70

sea

0.69

Activations Density 0.101%

professor names and associated institutions

positions or titles of professors associated with academic institutions

No Comments

No Known Activations