INDEX

Explanations

words related to security measures and procedures

oai_token-act-pair · gpt-3.5-turbo

terms related to security and protective measures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oric

-0.92

igible

-0.80

phrine

-0.77

hes

-0.75

sembly

-0.74

kson

-0.73

yss

-0.72

ting

-0.71

ufact

-0.70

ascar

-0.69

POSITIVE LOGITS

 guards

0.93

 clearance

0.90

 checkpoints

0.89

 breaches

0.86

 personnel

0.84

 checkpoint

0.82

 guard

0.81

policy

0.80

 screening

0.78

 Advis

0.78

Activations Density 0.047%

words related to security measures and procedures

terms related to security and protective measures

No Comments

No Known Activations