INDEX

Explanations

names or terms related to a specific entity named "Ka"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Ka" 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 @ 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

å§«

-0.98

IONS

-0.88

ROR

-0.86

âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ

-0.74

Ö¼

-0.73

EMENT

-0.73

Reading

-0.73

ECT

-0.72

flies

-0.71

POSITIVE LOGITS

Ka

1.12

Ka

1.06

isers

0.91

iser

0.91

iba

0.87

adian

0.87

 Klux

0.87

umat

0.86

adia

0.84

pler

0.84

Activations Density 0.009%

names or terms related to a specific entity named "Ka"

occurrences of the term "Ka" in various contexts

No Comments

No Known Activations