INDEX

Explanations

names of individuals, particularly those with the name "Ryan"

oai_token-act-pair · gpt-3.5-turbo

prominent names or figures associated with various contexts

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

Obj

-0.82

DATA

-0.76

manship

-0.75

HOME

-0.75

APH

-0.75

VALUE

-0.74

SOURCE

-0.73

#$#$

-0.73

FACE

-0.73

âĸ¬

-0.71

POSITIVE LOGITS

monds

0.74

sworth

0.69

zens

0.68

iggs

0.66

oker

0.65

idan

0.64

uckles

0.64

vik

0.63

fill

0.63

utter

0.62

Activations Density 0.305%

names of individuals, particularly those with the name "Ryan"

prominent names or figures associated with various contexts

No Comments

No Known Activations