INDEX

Explanations

proper nouns or titles highlighted by the term "Prim"

oai_token-act-pair · gpt-3.5-turbo

the term "Prim" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

lihood

-0.82

INESS

-0.80

olson

-0.73

IGH

-0.73

IELD

-0.71

UGH

-0.70

UGE

-0.67

DCS

-0.66

TPS

-0.65

aved

-0.65

POSITIVE LOGITS

itives

1.26

itive

1.14

 Prim

1.12

ordial

0.96

prim

0.93

archs

0.89

atis

0.88

arily

0.88

ument

0.87

Prim

0.85

Activations Density 0.007%

proper nouns or titles highlighted by the term "Prim"

the term "Prim" and its variations in different contexts

No Comments

No Known Activations