INDEX

Explanations

words related to research findings or outcomes

oai_token-act-pair · gpt-3.5-turbo

instances of the word "results."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

horn

-0.75

remember

-0.70

let

-0.69

ho

-0.67

audi

-0.67

abel

-0.66

haw

-0.64

irk

-0.64

 evangel

-0.63

 crou

-0.63

POSITIVE LOGITS

 results

3.74

results

3.00

 Results

2.71

 result

2.41

Results

2.16

 findings

1.93

result

1.92

 outcomes

1.80

 Result

1.69

 outcome

1.67

Activations Density 0.012%

words related to research findings or outcomes

instances of the word "results."

No Comments

No Known Activations