INDEX

Explanations

phrases related to actions and achievements

oai_token-act-pair · gpt-3.5-turbo

instances of negation and past tense actions

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

SPONSORED

-0.91

now

-0.83

Dialogue

-0.73

chron

-0.69

arel

-0.69

erno

-0.67

alias

-0.65

yah

-0.65

CLOSE

-0.64

associated

-0.64

POSITIVE LOGITS

 pione

0.87

EStream

0.83

 recently

0.82

 previously

0.79

 last

0.79

 earlier

0.79

 yesterday

0.78

 originally

0.78

ocument

0.72

 subur

0.68

Activations Density 0.508%

phrases related to actions and achievements

instances of negation and past tense actions

No Comments

No Known Activations