INDEX

Explanations

terms related to a specific topic mentioned as "GN."

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the acronym "GN" and its variations related to the nuclear energy sector

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

lies

-0.73

 Wink

-0.71

idas

-0.70

isSpecialOrderable

-0.70

orney

-0.68

quer

-0.68

cot

-0.67

bell

-0.66

mins

-0.62

minist

-0.61

POSITIVE LOGITS

SS

0.86

ocide

0.85

ostic

0.85

umeric

0.79

andan

0.77

OME

0.77

³

0.77

reens

0.76

vernment

0.75

ERAL

0.75

Activations Density 0.028%

terms related to a specific topic mentioned as "GN."

repeated mentions of the acronym "GN" and its variations related to the nuclear energy sector

No Comments

No Known Activations