INDEX

Explanations

expressions related to setting goals and aspirations

oai_token-act-pair · gpt-3.5-turbo

repeated patterns or symbols, particularly those that suggest confusion or nonsense

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pyramid

-0.81

 decomp

-0.77

 decom

-0.76

 carbohyd

-0.75

geries

-0.73

 mathemat

-0.73

 pressures

-0.73

 scram

-0.71

 weave

-0.71

 wagon

-0.70

POSITIVE LOGITS

ï¸ı

1.42

ï¸

1.02

Thankfully

0.84

 Thankfully

0.82

è£

0.82

 Therefore

0.82

Wr

0.80

âĶĢâĶĢâĶĢâĶĢ

0.80

TPS

0.79

laughs

0.79

Activations Density 0.153%

expressions related to setting goals and aspirations

repeated patterns or symbols, particularly those that suggest confusion or nonsense

No Comments

No Known Activations