INDEX

Explanations

phrases or names related to the name "Henry."

oai_token-act-pair · gpt-3.5-turbo

references to 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ramid

-0.93

ntil

-0.91

cheon

-0.90

awaru

-0.85

umbai

-0.80

ãĥ£

-0.79

*/(

-0.77

atively

-0.77

ittee

-0.76

olulu

-0.74

POSITIVE LOGITS

Tud

1.02

 Kissinger

0.98

 VIII

0.98

 Rollins

0.97

 Ford

0.92

Ell

0.86

 Hath

0.84

 Henry

0.83

 Miller

0.82

Wad

0.81

Activations Density 0.009%

phrases or names related to the name "Henry."

references to the name "Henry."

No Comments

No Known Activations