INDEX

Explanations

prepositions and prepositional phrases related to direction or location

oai_token-act-pair · gpt-3.5-turbo

relationships between actions and their consequences 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 @ 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

NES

-0.80

çĶ°

-0.72

Attempts

-0.71

itar

-0.68

REDACTED

-0.67

Ô

-0.66

IFE

-0.66

APTER

-0.65

EH

-0.63

RAG

-0.63

POSITIVE LOGITS

 themselves

0.81

 afar

0.73

©¶æ

0.73

 their

0.70

acas

0.66

 various

0.66

 nearby

0.64

 bios

0.64

their

0.64

 warehouses

0.63

Activations Density 0.720%

prepositions and prepositional phrases related to direction or location

relationships between actions and their consequences in various contexts

No Comments

No Known Activations