INDEX

Explanations

adjectives ending in 'al'

oai_token-act-pair · gpt-3.5-turbo

words associated with different types of professional divisions or classifications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nir

-0.68

atra

-0.65

icio

-0.64

stead

-0.63

stock

-0.63

Thor

-0.63

 McCoy

-0.63

 Hands

-0.61

peria

-0.61

 Hunt

-0.61

POSITIVE LOGITS

 behav

0.84

matically

0.76

ALLY

0.74

atically

0.74

theless

0.74

ascript

0.69

istically

0.67

 composition

0.64

 opin

0.64

 talents

0.62

Activations Density 0.181%

adjectives ending in 'al'

words associated with different types of professional divisions or classifications

No Comments

No Known Activations