INDEX

Explanations

years or time-related descriptions

oai_token-act-pair · gpt-3.5-turbo

significant numerical references, particularly concerning years

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

 fireplace

-0.71

Wall

-0.66

luent

-0.65

 meshes

-0.60

ierrez

-0.59

arms

-0.59

 circulate

-0.57

fired

-0.57

 violates

-0.57

 detects

-0.56

POSITIVE LOGITS

LEASE

0.83

 milestones

0.81

 tumultuous

0.78

eve

0.75

 anniversary

0.73

 testament

0.72

 fraught

0.72

 marked

0.72

 ausp

0.70

 pivotal

0.70

Activations Density 0.285%

years or time-related descriptions

significant numerical references, particularly concerning years

No Comments

No Known Activations