INDEX

Explanations

phrases related to government activities and procedures

oai_token-act-pair · gpt-3.5-turbo

terms related to governmental accountability and military presence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

die

-0.68

 mates

-0.66

byn

-0.65

 Rebell

-0.64

 lover

-0.61

 ensu

-0.61

å¥

-0.59

Others

-0.59

 groom

-0.57

Interstitial

-0.57

POSITIVE LOGITS

 FOIA

0.90

 jurisdiction

0.89

 oversight

0.82

ATF

0.78

classified

0.78

 regulatory

0.77

 prosecut

0.77

 authorization

0.75

 subpoen

0.74

 counterterrorism

0.73

Activations Density 1.164%

phrases related to government activities and procedures

terms related to governmental accountability and military presence

No Comments

No Known Activations