INDEX

Explanations

terms related to interception or interception-related actions

oai_token-act-pair · gpt-3.5-turbo

terms related to interception and surveillance activities

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

ened

-0.67

Aid

-0.65

jury

-0.62

 Alcohol

-0.61

cause

-0.60

Electric

-0.60

itsch

-0.60

chn

-0.59

zel

-0.59

Feel

-0.58

POSITIVE LOGITS

 intercepted

0.84

ibles

0.78

 intercept

0.77

IBLE

0.74

ible

0.71

ors

0.71

oute

0.70

aired

0.68

roit

0.68

ezvous

0.66

Activations Density 0.058%

terms related to interception or interception-related actions

terms related to interception and surveillance activities

No Comments

No Known Activations