INDEX

Explanations

phrases related to the handling or monitoring of various situations by specific entities

oai_token-act-pair · gpt-3.5-turbo

terms related to oversight and accountability in various contexts

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

adra

-0.70

Lay

-0.65

 arisen

-0.61

 Confeder

-0.59

Zone

-0.58

division

-0.55

layout

-0.55

fly

-0.54

liction

-0.54

chair

-0.54

POSITIVE LOGITS

ĸļ

0.85

 separately

0.83

igated

0.82

gew

0.81

escription

0.79

 administr

0.77

 individually

0.77

 extensively

0.77

uled

0.77

 differently

0.76

Activations Density 0.132%

phrases related to the handling or monitoring of various situations by specific entities

terms related to oversight and accountability in various contexts

No Comments

No Known Activations