INDEX

Explanations

elements or characteristics within a larger system

oai_token-act-pair · gpt-3.5-turbo

terms related to elements 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

sburgh

-0.76

ceed

-0.75

ctors

-0.75

rontal

-0.75

zee

-0.72

figured

-0.69

spe

-0.68

odore

-0.68

 Tribune

-0.65

lishing

-0.65

POSITIVE LOGITS

ality

0.96

als

0.92

 thereof

0.88

 elements

0.84

aries

0.79

witz

0.79

ARY

0.78

meal

0.77

 element

0.77

hetical

0.76

Activations Density 0.027%

elements or characteristics within a larger system

terms related to elements in various contexts

No Comments

No Known Activations