INDEX

Explanations

words related to branding or labeling

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "bl" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Gund

-0.75

reon

-0.65

 Democr

-0.64

 Solitaire

-0.64

HER

-0.62

Condition

-0.61

 Simulator

-0.61

 Gould

-0.60

pants

-0.59

depend

-0.59

POSITIVE LOGITS

anca

1.29

ossom

1.20

umenthal

1.13

anche

1.11

anco

1.09

acks

1.07

azer

1.06

izzard

1.01

itzer

1.01

oom

1.00

Activations Density 0.025%

words related to branding or labeling

occurrences of the word "bl" in various contexts

No Comments

No Known Activations