INDEX

Explanations

proper nouns or names related to a particular place

oai_token-act-pair · gpt-3.5-turbo

names and terms related to a specific location or entity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Sabha

-0.76

ppo

-0.72

LOAD

-0.71

Play

-0.70

ulkan

-0.69

tes

-0.68

BIT

-0.65

nexus

-0.63

 circulation

-0.61

ndra

-0.61

POSITIVE LOGITS

isd

1.21

ictional

1.00

ivers

0.88

ict

0.88

 epile

0.87

irect

0.87

aniel

0.83

iction

0.82

izzy

0.79

iving

0.78

Activations Density 0.010%

proper nouns or names related to a particular place

names and terms related to a specific location or entity

No Comments

No Known Activations