INDEX

Explanations

references to specific physical locations

oai_token-act-pair · gpt-3.5-turbo

references to rooms in various contexts

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

HER

-0.73

Uz

-0.69

Iss

-0.64

PB

-0.61

FIN

-0.61

 Accessed

-0.60

RBI

-0.60

elson

-0.59

 retribution

-0.58

FTA

-0.56

POSITIVE LOGITS

room

1.21

rooms

1.02

 rooms

0.96

 room

0.93

itory

0.87

 Room

0.86

 doors

0.85

 upstairs

0.81

 stalls

0.81

Room

0.80

Activations Density 0.030%

references to specific physical locations

references to rooms in various contexts

No Comments

No Known Activations