INDEX

Explanations

short forms of "dept" or "department"

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to detailed descriptions or evaluations

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

ãģĦ

-0.75

stroke

-0.69

owicz

-0.65

ãģĹ

-0.63

bat

-0.62

 dehyd

-0.61

iasis

-0.61

 gestures

-0.60

-0.58

atever

-0.58

POSITIVE LOGITS

wide

0.97

mates

0.94

 membership

0.87

 regulars

0.84

 mates

0.82

 members

0.79

 operated

0.78

mate

0.77

 member

0.77

 offices

0.76

Activations Density 0.782%

short forms of "dept" or "department"

words and phrases related to detailed descriptions or evaluations

No Comments

No Known Activations