INDEX

Explanations

occurrences of the suffix "en."

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

words related to people or specific individuals

oai_token-act-pair · gpt-3.5-turbo

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

 hitch

-0.74

 Canaveral

-0.67

enhagen

-0.66

 shake

-0.65

TPPStreamerBot

-0.64

milo

-0.64

 Jagu

-0.61

 Nicarag

-0.60

 tremend

-0.60

 reluct

-0.59

POSITIVE LOGITS

emies

1.36

chant

1.15

riched

1.08

zyme

1.06

wald

1.06

emy

1.05

bach

1.03

igmat

1.02

ews

1.01

esis

1.01

Activations Density 0.038%

occurrences of the suffix "en."

words related to people or specific individuals

No Comments

No Known Activations