INDEX

Explanations

pieces of computer code or technical information

oai_token-act-pair · gpt-3.5-turbo

technical terms and identifiers related to software and configurations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

drm

-0.55

 ..........

-0.54

osate

-0.53

 swat

-0.53

 amphib

-0.53

azo

-0.52

 coma

-0.51

otom

-0.50

anan

-0.50

 commercially

-0.50

POSITIVE LOGITS

heit

0.71

ngth

0.64

ername

0.58

Fn

0.58

wagon

0.57

riad

0.55

 Kinder

0.55

pse

0.54

worthiness

0.53

 downgrade

0.53

Activations Density 0.918%

pieces of computer code or technical information

technical terms and identifiers related to software and configurations

No Comments

No Known Activations