INDEX

Explanations

mentions of specific job titles, particularly related to legal positions like Attorney General

oai_token-act-pair · gpt-3.5-turbo

references to the position of Attorney General and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 deaf

-0.70

asted

-0.70

fry

-0.69

obyl

-0.67

bones

-0.66

 fracture

-0.65

 livest

-0.65

ombat

-0.64

din

-0.62

rophic

-0.62

POSITIVE LOGITS

 General

0.98

General

0.88

 Attorney

0.85

apolis

0.80

 Inspector

0.80

gency

0.77

alty

0.77

 Anth

0.75

Ins

0.75

alties

0.75

Activations Density 0.016%

mentions of specific job titles, particularly related to legal positions like Attorney General

references to the position of Attorney General and their actions

No Comments

No Known Activations