INDEX

Explanations

terms related to obstacles or hindrances

oai_token-act-pair · gpt-3.5-turbo

references to obstacles or impediments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ergy

-0.73

sch

-0.72

 largeDownload

-0.71

ovie

-0.69

ership

-0.67

serious

-0.66

orp

-0.66

sin

-0.65

rouse

-0.65

ribution

-0.65

POSITIVE LOGITS

 barriers

1.49

 barrier

1.30

 Barrier

1.05

 obstacles

0.88

riers

0.86

 walls

0.84

 wall

0.80

buster

0.79

 erected

0.79

 separating

0.77

Activations Density 0.008%

terms related to obstacles or hindrances

references to obstacles or impediments

No Comments

No Known Activations