INDEX

Explanations

phrases describing events or actions leading up to something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a sequence of events leading to a specific point in time

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

gans

-0.72

pload

-0.69

avorite

-0.67

pers

-0.64

Pers

-0.63

 Logged

-0.62

aren

-0.61

Filter

-0.61

cats

-0.61

 apples

-0.60

POSITIVE LOGITS

stairs

0.97

stage

0.96

actionDate

0.80

dating

0.75

WARD

0.74

 stairs

0.74

wards

0.72

uberty

0.71

grading

0.71

gradient

0.67

Activations Density 0.026%

phrases describing events or actions leading up to something

phrases indicating a sequence of events leading to a specific point in time

No Comments

No Known Activations