INDEX

Explanations

instances of the name "Henry" followed by a single-digit number

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Henry."

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

ramid

-0.92

awaru

-0.92

ntil

-0.92

cheon

-0.87

ãĥ£

-0.85

umbai

-0.80

*/(

-0.79

 teasp

-0.79

ittee

-0.78

acular

-0.77

POSITIVE LOGITS

Tud

1.02

 Rollins

1.02

 VIII

0.99

 Kissinger

0.98

 Ford

0.91

Wad

0.85

ford

0.84

 Hath

0.83

 Miller

0.81

Ell

0.78

Activations Density 0.017%

instances of the name "Henry" followed by a single-digit number

occurrences of the name "Henry."

No Comments

No Known Activations