INDEX

Explanations

keywords related to security and protection

oai_token-act-pair · gpt-3.5-turbo

terms related to security

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

irez

-0.67

udi

-0.65

price

-0.65

Buzz

-0.64

ovych

-0.64

oths

-0.63

 Louise

-0.62

hops

-0.62

govtrack

-0.61

VL

-0.61

POSITIVE LOGITS

 perimeter

0.83

 enclave

0.82

 cryptographic

0.81

 handshake

0.79

ment

0.77

rets

0.76

ments

0.76

 adolesc

0.73

 communications

0.72

Random

0.71

Activations Density 0.042%

keywords related to security and protection

terms related to security

No Comments

No Known Activations