INDEX

Explanations

names or titles with the suffix "Sr."

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals or titles, particularly with the prefix "Sr."

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

enaries

-0.80

insula

-0.71

iage

-0.69

sylvania

-0.68

 Dickinson

-0.65

ision

-0.64

 inhib

-0.63

umenthal

-0.63

govtrack

-0.61

ãĥī

-0.60

POSITIVE LOGITS

pered

0.90

é¾įåĸļå£«

0.81

 Chak

0.81

tis

0.81

pering

0.77

inka

0.77

nor

0.76

Lua

0.76

uve

0.73

Py

0.72

Activations Density 0.030%

names or titles with the suffix "Sr."

mentions of specific individuals or titles, particularly with the prefix "Sr."

No Comments

No Known Activations