INDEX

Explanations

specific individuals or entities within a larger context

oai_token-act-pair · gpt-3.5-turbo

mentions of specific roles or labels applied to individuals

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

abil

-0.67

alysis

-0.64

nance

-0.63

 sorts

-0.63

aeda

-0.63

 Arrows

-0.61

 Stage

-0.59

ogens

-0.59

hement

-0.59

position

-0.58

POSITIVE LOGITS

 apiece

0.76

anooga

0.73

 subp

0.73

hander

0.71

icka

0.70

opal

0.67

paio

0.66

icipated

0.64

 summed

0.64

uko

0.63

Activations Density 0.145%

specific individuals or entities within a larger context

mentions of specific roles or labels applied to individuals

No Comments

No Known Activations