INDEX

Explanations

specific terms related to technical processes or products

oai_token-act-pair · gpt-3.5-turbo

terms associated with specific programs, identifiers, or categorizations 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ±

-0.76

Bloom

-0.74

lad

-0.66

coll

-0.65

gro

-0.65

*=-

-0.63

Cor

-0.63

stream

-0.62

brook

-0.62

 Glas

-0.61

POSITIVE LOGITS

reciation

0.74

 itself

0.69

âĦ¢:

0.67

 hotline

0.67

 lease

0.64

 guid

0.63

 giveaway

0.63

 moniker

0.62

eas

0.62

FAQ

0.62

Activations Density 0.560%

specific terms related to technical processes or products

terms associated with specific programs, identifiers, or categorizations in various contexts

No Comments

No Known Activations