INDEX

Explanations

contexts where actions or decisions are aligned or consistent with something

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

CVE

-0.77

soever

-0.72

ilt

-0.70

DAC

-0.69

 livest

-0.59

 Horror

-0.58

 Lawyers

-0.58

iens

-0.58

rl

-0.57

 Bohem

-0.57

POSITIVE LOGITS

backer

0.87

meal

0.77

ups

0.75

arity

0.74

behind

0.70

wikipedia

0.69

 vein

0.68

asis

0.65

 behind

0.65

ridor

0.65

Activations Density 0.035%

contexts where actions or decisions are aligned or consistent with something

No Comments

No Known Activations