INDEX

Explanations

percentages or rates of change in data

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" and its relation to various statistics or rates

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

rang

-0.65

LOG

-0.65

ens

-0.63

ItemTracker

-0.61

edly

-0.61

killed

-0.60

HAEL

-0.60

username

-0.59

 nurt

-0.59

NOW

-0.58

POSITIVE LOGITS

 conjunction

1.10

ordinate

1.10

 accordance

1.09

clusively

1.09

 unison

1.08

efficiency

1.08

animate

1.05

clusions

1.03

 relation

1.03

versions

1.03

Activations Density 0.317%

percentages or rates of change in data

occurrences of the word "in" and its relation to various statistics or rates

No Comments

No Known Activations