INDEX

Explanations

years or numerical sequences representing specific years

oai_token-act-pair · gpt-3.5-turbo

numerical data, specifically relating to years and specific metrics

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

ãĤ¤ãĥĪ

-0.87

ivity

-0.85

ivities

-0.79

ique

-0.79

ICLE

-0.76

ional

-0.71

iques

-0.71

icles

-0.71

cil

-0.69

lier

-0.69

POSITIVE LOGITS

 externalToEVAOnly

1.00

0.84

mph

0.83

0.78

LECT

0.78

pora

0.78

porary

0.75

Activations Density 0.069%

years or numerical sequences representing specific years

numerical data, specifically relating to years and specific metrics

No Comments

No Known Activations