INDEX

Explanations

verbs related to various activities and actions carried out by individuals or groups

oai_token-act-pair · gpt-3.5-turbo

active verbs that imply action or participation

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

ãĤ´ãĥ³

-0.69

Downloadha

-0.59

 convol

-0.55

 tiss

-0.55

nih

-0.54

dating

-0.54

nikov

-0.54

enegger

-0.53

Nos

-0.52

 Seym

-0.51

POSITIVE LOGITS

uate

0.66

ISE

0.59

 RELEASE

0.55

enance

0.55

igate

0.54

him

0.54

itate

0.54

ulate

0.53

 them

0.51

IRE

0.50

Activations Density 0.496%

verbs related to various activities and actions carried out by individuals or groups

active verbs that imply action or participation

No Comments

No Known Activations