INDEX

Explanations

mentions of different locations and activities within those locations

oai_token-act-pair · gpt-3.5-turbo

descriptions of personal experiences and settings

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

emort

-0.71

 unequivocally

-0.64

 definitively

-0.64

azeera

-0.62

ERO

-0.62

erity

-0.61

rists

-0.61

hematically

-0.59

 accurately

-0.59

phabet

-0.58

POSITIVE LOGITS

 rented

0.86

 downtown

0.76

 convent

0.74

 tents

0.73

 monastery

0.73

 cafÃ©

0.71

 caravan

0.71

 mosqu

0.70

 makeshift

0.70

 dorm

0.70

Activations Density 1.012%

mentions of different locations and activities within those locations

descriptions of personal experiences and settings

No Comments

No Known Activations