INDEX

Explanations

posts containing the word "Posted"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Posted" and related display attributes in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ingly

-0.80

apter

-0.77

nut

-0.75

 Berman

-0.75

outer

-0.72

irsch

-0.71

services

-0.68

warts

-0.67

ministic

-0.66

ameda

-0.65

POSITIVE LOGITS

0.68

Sent

0.68

 Flames

0.64

ithe

0.61

cko

0.60

edin

0.60

 Cance

0.59

Blade

0.58

esville

0.58

cies

0.58

Activations Density 0.014%

posts containing the word "Posted"

occurrences of the word "Posted" and related display attributes in a document

No Comments

No Known Activations