INDEX

Explanations

references to individuals named "Lewis"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Lewis."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

iaries

-0.92

oat

-0.84

iary

-0.82

ologies

-0.78

ript

-0.77

uses

-0.76

untu

-0.75

icago

-0.73

ilial

-0.72

ities

-0.72

POSITIVE LOGITS

 Carroll

1.07

 Hamilton

0.93

burg

0.89

utenant

0.88

hurst

0.86

ohn

0.85

Hamilton

0.84

SON

0.84

peed

0.84

backer

0.81

Activations Density 0.044%

references to individuals named "Lewis"

occurrences of the name "Lewis."

No Comments

No Known Activations