INDEX

Explanations

buzzwords or terms related to news headlines and events

oai_token-act-pair · gpt-3.5-turbo

sentences that contain punctuation marks, particularly periods and question marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 seiz

-0.77

 favour

-0.73

 pudding

-0.71

 freezer

-0.70

 noise

-0.69

 hatch

-0.69

 raft

-0.69

 favor

-0.68

 gelatin

-0.67

 tens

-0.67

POSITIVE LOGITS

Imm

1.34

Hope

1.34

In

1.34

Nor

1.33

Again

1.32

As

1.30

To

1.30

Another

1.29

Different

1.29

For

1.29

Activations Density 0.262%

buzzwords or terms related to news headlines and events

sentences that contain punctuation marks, particularly periods and question marks

No Comments

No Known Activations