INDEX

Explanations

words related to sharpening or intensifying something

oai_token-act-pair · gpt-3.5-turbo

verbs that suggest a process of change or transformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

holding

-0.64

Sci

-0.62

 Semin

-0.62

 STEM

-0.62

puting

-0.60

 Terry

-0.59

 Nichols

-0.58

 Quad

-0.58

IBM

-0.57

 thirds

-0.57

POSITIVE LOGITS

ened

1.18

 guiActiveUn

1.04

inki

0.95

ening

0.94

ãĤ¬

0.90

undown

0.89

emies

0.89

redients

0.86

thens

0.86

ikuman

0.86

Activations Density 0.012%

words related to sharpening or intensifying something

verbs that suggest a process of change or transformation

No Comments

No Known Activations