INDEX

Explanations

phrases related to research findings or data analysis

oai_token-act-pair · gpt-3.5-turbo

references to research findings or outcomes

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

gger

-0.72

queue

-0.67

[_

-0.63

timer

-0.63

ifle

-0.63

 besides

-0.61

erson

-0.60

icker

-0.59

 forbid

-0.59

let

-0.58

POSITIVE LOGITS

 findings

3.46

 conclusions

1.99

 discoveries

1.91

 results

1.78

 observations

1.66

 recommendations

1.60

results

1.52

 insights

1.44

 hypotheses

1.42

 analyses

1.42

Activations Density 0.010%

phrases related to research findings or data analysis

references to research findings or outcomes

No Comments

No Known Activations