INDEX

Explanations

words related to significant events or achievements

oai_token-act-pair · gpt-3.5-turbo

references to significant historical events or 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

enhagen

-0.79

mar

-0.79

ritz

-0.73

avier

-0.73

ilial

-0.70

ensions

-0.70

ISO

-0.69

amar

-0.68

 Cosponsors

-0.68

 unfocusedRange

-0.67

POSITIVE LOGITS

 ever

1.04

 EVER

1.02

 imaginable

1.00

 humankind

0.87

 mankind

0.81

 possible

0.78

 therap

0.76

 Ever

0.73

ever

0.73

Ever

0.72

Activations Density 0.289%

words related to significant events or achievements

references to significant historical events or contexts

No Comments

No Known Activations