INDEX

Explanations

phrases indicating lack of association or relevance

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the lack of relevance or connection

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

©¶æ¥µ

-0.88

kept

-0.74

psons

-0.72

 polled

-0.70

hiba

-0.68

marg

-0.68

umper

-0.67

ÂłÂłÂłÂłÂłÂłÂłÂł

-0.67

fal

-0.66

warn

-0.66

POSITIVE LOGITS

 regard

0.69

 determining

0.68

 what

0.65

 deciding

0.65

 fixing

0.65

 selecting

0.62

 destiny

0.61

 regards

0.61

 respecting

0.61

 designing

0.60

Activations Density 0.036%

phrases indicating lack of association or relevance

phrases emphasizing the lack of relevance or connection

No Comments

No Known Activations