INDEX

Explanations

phrases related to tasks or activities, especially when accompanied by verbs

oai_token-act-pair · gpt-3.5-turbo

phrases related to jobs and accomplishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Phase

-0.67

"-

-0.65

 "...

-0.65

Transform

-0.61

Van

-0.60

Unix

-0.60

 charism

-0.59

Focus

-0.58

``

-0.56

Ang

-0.56

POSITIVE LOGITS

chester

0.79

ngth

0.75

',

0.75

anty

0.71

REF

0.70

apest

0.70

undred

0.70

respond

0.69

redd

0.69

ggle

0.68

Activations Density 0.312%

phrases related to tasks or activities, especially when accompanied by verbs

phrases related to jobs and accomplishments

No Comments

No Known Activations