INDEX

Explanations

names starting with "Ra"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the sequence "ra" 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iaries

-0.74

regor

-0.73

lace

-0.67

OW

-0.66

 curfew

-0.65

ĳå£«

-0.64

 Revel

-0.63

DW

-0.62

 charism

-0.61

CW

-0.61

POSITIVE LOGITS

irie

1.31

fter

1.25

fters

1.20

ven

1.17

eus

1.16

ving

1.08

ffe

1.08

plets

1.07

zzo

1.07

ppy

1.05

Activations Density 0.029%

names starting with "Ra"

occurrences of the sequence "ra" in various contexts

No Comments

No Known Activations