INDEX

Explanations

mentions of the word "Mangan"

oai_token-act-pair · gpt-3.5-turbo

references to the term "gan" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ension

-0.69

 differential

-0.67

ensions

-0.66

ractive

-0.64

İĭ

-0.64

Reference

-0.63

suit

-0.62

 fundament

-0.61

 Topic

-0.61

Peg

-0.60

POSITIVE LOGITS

igans

1.06

za

0.94

omal

0.93

non

0.93

agher

0.93

cia

0.92

ogly

0.92

istan

0.91

ja

0.91

igan

0.91

Activations Density 0.023%

mentions of the word "Mangan"

references to the term "gan" in various contexts

No Comments

No Known Activations